© 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. 215815
    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
     Milton
    0.38
    ullan
    0.37
     waited
    0.37
     Jockey
    0.36
    Lycodon
    0.35
     Fancy
    0.34
     vinho
    0.33
    ≒
    0.33
     liberty
    0.33
     Operator
    0.33
    POSITIVE LOGITS
    adrenaline
    0.44
     ਸੰ
    0.42
     atrib
    0.42
    vocab
    0.39
     रोडवेज
    0.39
    mu
    0.39
     potř
    0.39
     đo
    0.39
     dien
    0.39
     atribu
    0.38
    Activations Density 0.000%

    No Known Activations