© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80777
    Prev
    Next
    INDEX
    Explanations

    QApplication usage in Python

    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_31_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
     காற்றின்
    0.38
    藉
    0.36
    レンタ
    0.35
    是通过
    0.34
    ందు
    0.33
    দেবের
    0.33
    通过
    0.33
    butoxy
    0.33
    湘
    0.32
     директора
    0.32
    POSITIVE LOGITS
     internally
    0.37
     -=
    0.36
     Bod
    0.36
    Fal
    0.36
    interpolate
    0.35
     އި
    0.35
    Bod
    0.34
    Hill
    0.34
    -=
    0.34
    inge
    0.33
    Activations Density 0.000%

    No Known Activations