© 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. 161073
    Prev
    Next
    INDEX
    Explanations

    keep in mind

    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
    ه
    1.25
    is
    1.20
    ed
    1.19
    ే
    1.18
    in
    1.16
    هي
    1.14
    د
    1.14
    ى
    1.14
    ാ
    1.13
    ча
    1.12
    POSITIVE LOGITS
    t
    1.32
    the
    1.25
    AL
    1.18
    '
    1.16
    gana
    1.02
    st
    1.02
    gi
    1.01
    𝓬
    0.98
    ное
    0.96
    tive
    0.96
    Activations Density 0.006%

    No Known Activations