© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13781
    Prev
    Next
    INDEX
    Explanations

    the number of credits needed to pass a grade in areas of study

    oai_token-act-pair · gemini-2.0-flash

    school and education

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Roskov
    -0.70
    IGraphics
    -0.61
    __':
    -0.59
    gonic
    -0.58
    FormTagHelper
    -0.55
     endfor
    -0.55
    __":
    -0.54
    setof
    -0.53
    basicConfig
    -0.53
    Kaieteur
    -0.53
    POSITIVE LOGITS
     éducation
    0.58
    ://$
    0.57
    LLocation
    0.57
    expandindo
    0.56
    ValueStyle
    0.53
     Winaray
    0.52
     censura
    0.52
    StructEnd
    0.52
     generazione
    0.51
     partecipazione
    0.51
    Activations Density 1.981%

    No Known Activations