© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46291
    Prev
    Next
    INDEX
    Explanations

    ```randomly assign```

    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_3_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
    in
    0.80
    u
    0.62
    ide
    0.60
    Т
    0.60
    erve
    0.59
    reservoir
    0.59
    ை
    0.57
    as
    0.55
     mee
    0.55
    pe
    0.55
    POSITIVE LOGITS
    ς
    0.80
    s
    0.64
    نی
    0.63
     powied
    0.63
     aument
    0.61
    いう
    0.60
    sPath
    0.58
    یم
    0.58
    ی
    0.56
     parcours
    0.56
    Activations Density 0.009%

    No Known Activations