© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52492
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    хова
    0.36
     =====
    0.36
    abhavena
    0.35
    škai
    0.35
    न्तु
    0.35
     ux
    0.34
     хал
    0.33
    =");
    0.32
     云
    0.32
     ？
    0.32
    POSITIVE LOGITS
    Your
    0.48
    With
    0.48
     You
    0.46
    Despite
    0.46
     Despite
    0.45
     Yours
    0.45
    Yours
    0.44
     Some
    0.43
     Since
    0.43
    Some
    0.43
    Activations Density 0.005%

    No Known Activations