© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197823
    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_9_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
     hv
    0.50
    駋
    0.49
    ходом
    0.48
    όμε
    0.48
    勖
    0.48
    nCurr
    0.48
     muy
    0.48
     controllo
    0.47
    拷贝
    0.46
    meldung
    0.46
    POSITIVE LOGITS
    ار
    0.46
     slumped
    0.44
     KO
    0.44
     subordinate
    0.43
     opportune
    0.43
    同梱
    0.42
     beset
    0.42
    お
    0.42
     indoctr
    0.42
     demands
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.