© 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. 202970
    Prev
    Next
    INDEX
    Explanations

    max-width:

    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
    ђено
    0.39
    霏
    0.39
    ченной
    0.35
    дон
    0.34
    劾
    0.34
    ্তিক
    0.33
    甚至
    0.32
    μαι
    0.32
    ниці
    0.32
    ζεται
    0.32
    POSITIVE LOGITS
    ?
    0.38
    0.37
    ost
    0.35
    erst
    0.34
     i
    0.34
    ern
    0.34
    l
    0.33
    services
    0.33
     primes
    0.33
     ruby
    0.32
    Activations Density 0.000%

    No Known Activations