© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209654
    Prev
    Next
    INDEX
    Explanations

    Z-Mount, Z-index, Z-score, Z-Machine, Z-Moves

    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_10_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
    0
    0.85
    .
    0.75
    }.
    0.74
    ).[
    0.73
    )
    0.70
    }
    0.69
    ).
    0.68
    ij
    0.66
    ())
    0.66
     सप्टेंबर
    0.64
    POSITIVE LOGITS
    로
    0.85
    ת
    0.74
     maisons
    0.73
    ल
    0.70
    ur
    0.68
    ל
    0.68
     artistas
    0.66
     eyep
    0.66
    라
    0.66
     attacks
    0.66
    Activations Density 0.008%

    No Known Activations