© 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. 15886
    Prev
    Next
    INDEX
    Explanations

    the word "no" and related negative words like "not" or "never," often near other important keywords.

    oai_token-act-pair · gemini-2.0-flash

    No

    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
    no
    -0.54
    No
    -0.54
     NO
    -0.53
     No
    -0.52
    //
    -0.50
     no
    -0.48
    NO
    -0.47
    izr
    -0.44
    */].
    -0.44
    ()];
    -0.42
    POSITIVE LOGITS
     للمعارف
    0.80
    IUrlHelper
    0.77
    帖最后由
    0.76
     الحره
    0.75
    VersionUID
    0.74
    UnsafeEnabled
    0.74
     defaultstate
    0.72
    Portale
    0.68
    StoreMessageInfo
    0.68
    contentLoaded
    0.67
    Activations Density 4.209%

    No Known Activations