© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12518
    Prev
    Next
    INDEX
    Explanations

    java code including imports and comments

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    tok
    -0.44
     araw
    -0.43
    all
    -0.42
     Harn
    -0.42
    lexia
    -0.41
     Feind
    -0.41
     huwa
    -0.40
    <eos>
    -0.40
    item
    -0.40
     Glance
    -0.40
    POSITIVE LOGITS
     MediatR
    1.02
    ArgsConstructor
    0.88
     protoimpl
    0.88
    migrationBuilder
    0.86
     NgModule
    0.84
     BorderRadius
    0.84
     sqlalchemy
    0.81
    springframework
    0.80
    StoryboardSegue
    0.78
    addCriterion
    0.77
    Activations Density 0.788%

    No Known Activations