© 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. 6833
    Prev
    Next
    INDEX
    Explanations

    phrases which are subjective opinions or judgements

    oai_token-act-pair · gemini-2.0-flash

    is

    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
    Демографія
    -0.80
    httphttps
    -0.68
    }>;
    -0.63
    UseVisualStyle
    -0.63
    "))
    -0.62
     CURIAM
    -0.61
     simplifié
    -0.58
    )}</
    -0.57
    "));
    -0.57
    VolleyError
    -0.57
    POSITIVE LOGITS
    :✨
    0.58
     érté
    0.54
    shadowOffset
    0.53
    /*++
    0.52
     isComment
    0.50
    ORB
    0.48
     αξ
    0.47
     Men
    0.47
    VALUE
    0.46
     pedal
    0.46
    Activations Density 2.137%

    No Known Activations