© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4490
    Prev
    Next
    INDEX
    Explanations

    names of people and/or references for sources

    oai_token-act-pair · gemini-2.0-flash

    Academic text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     pro
    -0.53
     top
    -0.49
    pro
    -0.49
    со
    -0.46
     
    -0.45
    5
    -0.44
     people
    -0.43
    ↵↵
    -0.42
     value
    -0.40
    v
    -0.39
    POSITIVE LOGITS
     nahilalakip
    1.28
     autorytatywna
    1.22
    Tikang
    1.19
     CreateTagHelper
    1.17
    rrggbb
    1.17
    tagHelperRunner
    1.14
     мәкал
    1.12
    ArgsConstructor
    1.11
    OGND
    1.09
    IntoConstraints
    1.09
    Activations Density 0.894%

    No Known Activations