© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45411
    Prev
    Next
    INDEX
    Explanations

    viper, moccasin, adder, toxins

    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_13_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
     অপরাধ
    0.49
     அவற்றை
    0.45
     satirical
    0.44
     horoscope
    0.43
    ChessBot
    0.43
     referral
    0.42
    柬
    0.42
    stripos
    0.42
    가를
    0.42
    CO
    0.42
    POSITIVE LOGITS
    it
    0.56
     gusta
    0.55
     graag
    0.52
     zien
    0.52
    ম
    0.51
    prüng
    0.51
    𝐧
    0.51
    ര്‍ന്ന
    0.50
     dand
    0.50
     thrilled
    0.50
    Activations Density 0.000%

    No Known Activations