© 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. 236434
    Prev
    Next
    INDEX
    Explanations

    pip install -e

    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
     motions
    0.43
     occupants
    0.38
    AudioManager
    0.38
     grouping
    0.37
     हुई
    0.37
     COc
    0.37
     excelled
    0.37
    🚦
    0.37
    getZoom
    0.36
     quarrels
    0.36
    POSITIVE LOGITS
     vald
    0.37
    ukai
    0.36
    ரி
    0.35
    MAC
    0.35
    нь
    0.35
     según
    0.35
    RIBE
    0.34
    Lac
    0.34
    эс
    0.34
    OFF
    0.34
    Activations Density 0.000%

    No Known Activations