© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199108
    Prev
    Next
    INDEX
    Explanations

    response formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    O
    0.58
    After
    0.49
    Al
    0.48
    OL
    0.48
    void
    0.48
    King
    0.48
    Aqu
    0.48
    Being
    0.48
     mêmes
    0.47
    E
    0.47
    POSITIVE LOGITS
    sala
    0.50
    ̉a
    0.48
    credited
    0.47
    ין
    0.46
     консульта
    0.46
     ચૂક
    0.46
     к
    0.46
    etica
    0.45
    тт
    0.45
    েও
    0.45
    Activations Density 0.000%

    No Known Activations