© 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. 203720
    Prev
    Next
    INDEX
    Explanations

    can help and offer information

    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
    irteen
    0.36
    uits
    0.35
    viving
    0.35
    Structured
    0.35
    ଭ
    0.34
    ies
    0.34
    triangleleft
    0.34
     triumphs
    0.34
     tranquillity
    0.34
    inkl
    0.34
    POSITIVE LOGITS
    ،
    0.42
    吘
    0.38
    সরকারী
    0.38
     LOVE
    0.37
    LOVE
    0.37
    ।]
    0.36
     اج
    0.36
     بش
    0.36
     éx
    0.36
     pois
    0.36
    Activations Density 0.016%

    No Known Activations