© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15494
    Prev
    Next
    INDEX
    Explanations

    text discussing how something should be interpreted

    oai_token-act-pair · gemini-2.0-flash

    interpreting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Efq
    -0.68
     caufe
    -0.66
    #+#
    -0.65
     houſe
    -0.65
     itſelf
    -0.65
     cauſe
    -0.65
    aronne
    -0.63
     chofe
    -0.62
     ſmall
    -0.62
     Reſ
    -0.59
    POSITIVE LOGITS
     interpreting
    0.64
     Interpreting
    0.63
     Interpret
    0.61
     interpret
    0.61
     interpretar
    0.58
    Interpret
    0.57
    interprétation
    0.57
     INTERPRET
    0.55
     onPostExecute
    0.54
     meaning
    0.54
    Activations Density 2.572%

    No Known Activations