© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144573
    Prev
    Next
    INDEX
    Explanations

    literary names, punctuation, code, speech acts

    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_0_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
     for
    1.76
    ر
    1.29
    ม
    1.27
    ت
    1.23
    '}
    1.13
    }
    1.12
    )،
    1.11
     beers
    1.10
    <h3>
    1.09
     =
    1.09
    POSITIVE LOGITS
    ing
    1.70
    v
    1.65
    p
    1.48
    le
    1.45
    c
    1.40
    g
    1.40
    io
    1.38
    ra
    1.36
    beth
    1.27
    я
    1.24
    Activations Density 0.000%

    No Known Activations