© 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. 61776
    Prev
    Next
    INDEX
    Explanations

    names ending in ville, botanical terms

    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
     чувство
    1.14
    h
    1.12
    '
    1.05
    น้ำ
    1.04
    ’
    0.98
    <0x92>
    0.93
    <0x82>
    0.89
    <0xAB>
    0.88
    )$:
    0.88
    <0x91>
    0.87
    POSITIVE LOGITS
     for
    2.14
    is
    1.84
     from
    1.46
     to
    1.45
    t
    1.38
    m
    1.37
    ী
    1.27
    ir
    1.25
    5
    1.25
    ó
    1.22
    Activations Density 0.000%

    No Known Activations