© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7598
    Prev
    Next
    INDEX
    Explanations

    words related to film reviews or fashion

    oai_token-act-pair · gemini-2.0-flash

    interpretations and analysis

    np_token-act-pair-logits · gpt-4o-mini

    interpretation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     مشين
    -0.65
    ItemBackground
    -0.63
     Ressource
    -0.61
     ويكيپيديا
    -0.61
    AddTagHelper
    -0.60
    providedIn
    -0.57
     joaat
    -0.57
    HandlerContext
    -0.57
     @"/
    -0.56
    Enllaces
    -0.56
    POSITIVE LOGITS
     interpretation
    0.74
    interpretation
    0.67
     answer
    0.66
     take
    0.60
     statement
    0.59
     Interpretation
    0.59
     approach
    0.57
    NewUrlParser
    0.57
     treatment
    0.56
    interpret
    0.56
    Activations Density 2.020%

    No Known Activations