© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5632
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and symbols

    oai_token-act-pair · gemini-2.0-flash

    mathematical symbols and hyphens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    +#+#
    -1.02
    enumi
    -0.98
     للاسماء
    -0.94
     Efq
    -0.93
     Мексичка
    -0.93
    ValueStyle
    -0.92
     ddelweddau
    -0.92
    Personendaten
    -0.90
    rrggbb
    -0.90
    KommentareTeilen
    -0.88
    POSITIVE LOGITS
    -
    0.96
    —
    0.68
    -\
    0.66
    (
    0.66
    _
    0.63
    –
    0.63
    -(
    0.57
    --
    0.57
    +
    0.56
     —
    0.53
    Activations Density 6.351%

    No Known Activations