© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15041
    Prev
    Next
    INDEX
    Explanations

    different clauses, in particular the last example talks about fashion and things falling apart

    oai_token-act-pair · gemini-2.0-flash

    problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    الحياه
    -0.70
     Roskov
    -0.54
     <=",
    -0.53
     visibilité
    -0.51
    Karakteristik
    -0.49
    quelize
    -0.49
    createFrom
    -0.49
    rewsbury
    -0.49
    Referències
    -0.49
    CppCodeGen
    -0.45
    POSITIVE LOGITS
     initComponents
    0.91
    UserScript
    0.75
    IsContent
    0.66
    ImageContext
    0.65
    InputBorder
    0.65
     MainAxisSize
    0.65
     typelib
    0.64
    ftagPool
    0.63
    __":
    0.59
    CloseOperation
    0.58
    Activations Density 0.943%

    No Known Activations