© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217286
    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
     mLast
    0.22
    imidazol
    0.21
     COSTS
    0.20
     دا
    0.20
     imidazol
    0.20
     varias
    0.19
    布
    0.19
     trav
    0.19
    Purple
    0.19
     defaults
    0.18
    POSITIVE LOGITS
    OH
    0.25
    ヒト
    0.25
     ჰ
    0.25
    nhs
    0.25
     LHS
    0.24
     human
    0.24
     Haush
    0.23
     hardness
    0.23
     hydroxide
    0.23
    𝐻
    0.23
    Activations Density 0.000%

    No Known Activations