© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1738
    Prev
    Next
    INDEX
    Explanations

    Kühlkette, food, criteria, basic allowance, trading

    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_39_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
     साउंड
    0.39
    Falcon
    0.39
     appetizing
    0.38
     Spicy
    0.38
     troubled
    0.37
     }^{(
    0.37
     Sublime
    0.37
    ccedil
    0.37
    Pren
    0.37
     Pren
    0.37
    POSITIVE LOGITS
    ≙
    0.47
     Kein
    0.46
    aktual
    0.43
    sung
    0.43
     raus
    0.43
     Leverkusen
    0.42
     Kreuz
    0.42
     beobachten
    0.41
     Bildung
    0.41
     Mainz
    0.41
    Activations Density 0.061%

    No Known Activations