© 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. 2855
    Prev
    Next
    INDEX
    Explanations

    instances of the word "out" followed by "of" or another word starting with "m"

    oai_token-act-pair · gemini-2.0-flash

    phrases related to "out"

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

    out

    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
    MLLoader
    -0.68
    #
    -0.61
    raszam
    -0.53
    ArrowToggle
    -0.53
    RenderAtEndOf
    -0.53
    (:,:,
    -0.50
     Cuenca
    -0.49
     nargin
    -0.49
    PreExecute
    -0.49
    amemnon
    -0.49
    POSITIVE LOGITS
    mo
    0.57
    arpa
    0.52
    Portail
    0.51
    end
    0.50
    Exit
    0.50
    EnumValue
    0.50
    Calla
    0.48
    ligg
    0.48
    arama
    0.48
    Ί
    0.46
    Activations Density 0.654%

    No Known Activations