© 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. 108183
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ↵
    1.67
    ט
    1.30
    ز
    1.24
    ాలు
    1.09
    માં
    1.05
    <0xA8>
    1.04
    ین
    1.02
    ิบ
    1.02
    ں
    1.02
    ش
    1.01
    POSITIVE LOGITS
     are
    1.41
    রামর্শ
    1.19
    した
    1.10
     of
    1.05
     at
    1.00
    ೂರ್ವ
    0.99
    "，
    0.93
    天
    0.93
    "')
    0.92
    หนด
    0.90
    Activations Density 0.000%

    No Known Activations