© 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. 7315
    Prev
    Next
    INDEX
    Explanations

    instances of the string "Cas" followed by lowercase letters

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the token "Cas"

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

    Cas

    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
    providedIn
    -0.60
    ConstraintMaker
    -0.52
    round
    -0.50
    own
    -0.50
     town
    -0.50
    town
    -0.49
    ffekt
    -0.48
    owns
    -0.47
     Sachsen
    -0.46
    maka
    -0.46
    POSITIVE LOGITS
     ddelweddau
    0.81
    RenderAtEndOf
    0.75
     فريبيس
    0.69
    ⓧ
    0.66
     bezeichneter
    0.60
    WithIOException
    0.58
     TextAppearance
    0.57
     Undeclared
    0.55
     שוליים
    0.54
    #
    0.54
    Activations Density 0.305%

    No Known Activations