© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229780
    Prev
    Next
    INDEX
    Explanations

    cobbler, coburg, cobblestone, cobras, cobots, cobro

    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_6_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
    },
    1.02
    ).}
    1.02
    ),
    0.96
    ,
    0.95
    ;
    0.93
     innovations
    0.92
    )
    0.92
    ى
    0.91
    }\
    0.91
     inscriptions
    0.91
    POSITIVE LOGITS
    a
    1.33
    the
    1.22
    an
    1.16
    no
    1.03
    am
    1.02
    na
    1.00
    li
    0.99
    ne
    0.94
    p
    0.94
    م
    0.93
    Activations Density 0.000%

    No Known Activations