© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7031
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe changes, actions and status

    oai_token-act-pair · gemini-2.0-flash

    words related to development and investigation

    np_token-act-pair-logits · gpt-4o-mini

    actions being performed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.82
     snippetHide
    -0.81
    NewUrlParser
    -0.77
    цездатний
    -0.72
    rhosis
    -0.67
    ंदीखरीदारी
    -0.67
     excru
    -0.64
    mtrl
    -0.63
     Autorizaciones
    -0.63
    ReusableCell
    -0.61
    POSITIVE LOGITS
     by
    0.57
    Glorious
    0.51
     voorbij
    0.49
     refroid
    0.48
     pareti
    0.48
     sœurs
    0.47
     giacca
    0.45
     separating
    0.45
    BaseController
    0.45
     kinerja
    0.45
    Activations Density 6.167%

    No Known Activations