© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35998
    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_31_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
    abord
    0.45
    ov
    0.39
    Nc
    0.39
    Paid
    0.39
    long
    0.38
    Many
    0.38
    鲸
    0.38
     користу
    0.38
    xy
    0.37
    <0xD5>
    0.37
    POSITIVE LOGITS
     作り
    0.43
     Länge
    0.39
    ზრ
    0.38
    ទំន
    0.37
    🤠
    0.36
    💰
    0.35
     Peterborough
    0.35
    ፡፡
    0.35
     benöt
    0.35
     hely
    0.35
    Activations Density 0.000%

    No Known Activations