© 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. 61785
    Prev
    Next
    INDEX
    Explanations

    pillars

    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
    리
    1.48
    c
    1.09
    ла
    0.98
    d
    0.92
    ED
    0.91
    ਰ
    0.91
    ين
    0.90
    y
    0.90
    wl
    0.88
    ல்
    0.88
    POSITIVE LOGITS
    ’
    1.45
    '
    1.34
    ためには
    1.05
    </td>
    0.97
    ために
    0.93
    К
    0.91
    ین
    0.88
    th
    0.87
    5
    0.86
    ↵
    0.84
    Activations Density 0.001%

    No Known Activations