© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198952
    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_12_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
    t
    0.18
    "
    0.17
    ”
    0.17
    ation
    0.16
    g
    0.16
    Black
    0.16
    there
    0.16
    Highlight
    0.15
    ist
    0.15
    urgia
    0.15
    POSITIVE LOGITS
     ongeveer
    0.18
     Lors
    0.17
     ставак
    0.17
     verhindert
    0.17
     COMPET
    0.17
     awarded
    0.16
     দুর্বল
    0.16
     Л
    0.16
     ର
    0.16
     حوالي
    0.16
    Activations Density 0.000%

    No Known Activations