© 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. 202849
    Prev
    Next
    INDEX
    Explanations

    does this feel good

    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_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
    嗓
    0.47
    相同
    0.46
     здания
    0.46
    {};
    0.45
     আকাঙ্
    0.44
     volumetric
    0.44
     PlayerSelector
    0.44
     городской
    0.44
    쳥
    0.43
    𝟎
    0.43
    POSITIVE LOGITS
    ši
    0.48
    či
    0.47
     silly
    0.47
    Cheat
    0.46
     Cheese
    0.46
     OE
    0.45
    Nice
    0.45
     CE
    0.45
    ן
    0.44
    Quiz
    0.44
    Activations Density 0.001%

    No Known Activations