© 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-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61424
    Prev
    Next
    INDEX
    Explanations

    words starting with tas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     an
    1.26
    S
    1.18
    ,
    1.10
     a
    1.09
    N
    1.05
    T
    1.05
    }
    1.03
    ")
    1.02
    "}
    0.98
    $)$.
    0.97
    POSITIVE LOGITS
    ле
    1.54
    ли
    1.40
    inį
    1.18
    ਆਂ
    1.13
    ால்
    1.12
    ים
    1.11
    iin
    1.11
    in
    1.10
    ओं
    1.08
    s
    1.06
    Activations Density 0.000%

    No Known Activations