© 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. 14466
    Prev
    Next
    INDEX
    Explanations

    variations of the words 'awesomer,' 'coworkers,' 'hawkins,' and 'suck'

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "Cow" and "Haw"

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

    aw

    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
    ftagPool
    -0.67
    WebElementEntity
    -0.60
     ujednoznacz
    -0.58
    ypep
    -0.53
     الحره
    -0.53
    LookAnd
    -0.52
    SourceChecksum
    -0.52
    DESCRIP
    -0.50
    Jeografia
    -0.49
    OGND
    -0.48
    POSITIVE LOGITS
    waitKey
    0.54
     AttributeSet
    0.53
     snippetHide
    0.53
    /**
    0.51
    HomeAsUpEnabled
    0.50
     FileInputStream
    0.50
     varargin
    0.50
     TAMBÉM
    0.49
     ویکی‌پدیای
    0.49
     NDEBUG
    0.48
    Activations Density 0.413%

    No Known Activations