© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240872
    Prev
    Next
    INDEX
    Explanations

    private declarations

    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_25_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
    POINT
    0.40
    While
    0.39
    を書
    0.39
     fish
    0.38
     Couldn
    0.37
     Granger
    0.36
     ス
    0.36
     書
    0.35
     نہیں
    0.35
    ትር
    0.35
    POSITIVE LOGITS
    desIP
    0.39
     ඔ
    0.39
     principais
    0.39
    汲
    0.38
    emulator
    0.38
     calon
    0.38
    灞
    0.38
    zechos
    0.37
    ສ່ວນ
    0.37
     सहयोगी
    0.37
    Activations Density 0.000%

    No Known Activations