© 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. 11841
    Prev
    Next
    INDEX
    Explanations

    C code

    oai_token-act-pair · gemini-2.0-flash

    (

    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
    Brainz
    -0.60
     MainAxisSize
    -0.58
    AsUp
    -0.57
    HideFlags
    -0.57
    enderror
    -0.57
     незавершена
    -0.57
    AnchorStyles
    -0.56
    NameInMap
    -0.54
    Geplaatst
    -0.53
     Superhost
    -0.52
    POSITIVE LOGITS
    GLuint
    0.58
    volatile
    0.53
    SysUser
    0.51
    conditionally
    0.50
    NSIndexPath
    0.49
    CharCode
    0.49
    Izvori
    0.48
    s
    0.48
    SEGUIR
    0.47
    ulong
    0.46
    Activations Density 7.110%

    No Known Activations