© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197543
    Prev
    Next
    INDEX
    Explanations

    needy

    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_4_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
    ر
    1.20
    ام
    1.13
    ม
    1.09
    ي
    1.00
    م
    0.99
    ти
    0.98
    ной
    0.98
    ных
    0.97
    ный
    0.97
    타
    0.96
    POSITIVE LOGITS
    le
    1.22
    la
    1.15
     to
    1.12
    g
    1.07
    ra
    1.06
    d
    1.06
    *
    1.06
    3
    1.05
    ?
    1.04
    :
    1.02
    Activations Density 0.002%

    No Known Activations