© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194015
    Prev
    Next
    INDEX
    Explanations

    mlb

    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_4_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
    os
    1.22
    on
    1.16
    am
    1.08
    AN
    1.01
    AK
    1.00
    is
    0.99
    ي
    0.98
    IC
    0.95
    UN
    0.92
    ت
    0.90
    POSITIVE LOGITS
    )
    0.97
    ).
    0.94
    :
    0.91
    ;
    0.90
     chagrin
    0.80
    -
    0.78
    ),
    0.77
    ]
    0.76
    вання
    0.74
     пред
    0.73
    Activations Density 0.000%

    No Known Activations