© 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. 14075
    Prev
    Next
    INDEX
    Explanations

    locations and things related to locations that a person might visit

    oai_token-act-pair · gemini-2.0-flash

    elements related to geographical locations and names

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

    Florida locations and legal texts

    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
     die
    -0.50
     turno
    -0.41
    ēju
    -0.39
    UnknownFields
    -0.39
     capuche
    -0.38
     Man
    -0.38
    ామ
    -0.38
    ävän
    -0.38
     rencontré
    -0.37
     keting
    -0.37
    POSITIVE LOGITS
     CURIAM
    0.83
     continúas
    0.70
     Efq
    0.70
    WriteBarrier
    0.70
    Vidite
    0.69
    DoubleQuotes
    0.68
    AddTagHelper
    0.66
    TestingModule
    0.64
    #+#
    0.63
     Teas
    0.62
    Activations Density 0.614%

    No Known Activations