© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200839
    Prev
    Next
    INDEX
    Explanations

    progress bar

    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_6_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
    c
    1.49
    d
    1.38
    h
    1.30
    v
    1.29
    es
    1.13
    ə
    1.03
    and
    1.02
    g
    1.00
    ci
    0.98
    ၇
    0.98
    POSITIVE LOGITS
    '
    1.34
    ي
    1.32
    <0x0D>
    1.16
    يا
    1.07
    يان
    0.99
    يث
    0.96
    </h3>
    0.95
    ется
    0.95
    ل
    0.95
    י
    0.92
    Activations Density 0.000%

    No Known Activations