© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123217
    Prev
    Next
    INDEX
    Explanations

    HTML (HyperText Markup Language)

    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_3_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
    д
    0.82
    د
    0.82
    ۰
    0.74
    드
    0.71
     decentral
    0.66
    に
    0.63
    のは
    0.62
     revolutionary
    0.60
    ौ
    0.60
    צל
    0.59
    POSITIVE LOGITS
    1
    0.93
    i
    0.85
    _
    0.85
    2
    0.83
    ’
    0.82
     Diem
    0.80
    et
    0.76
    ’,
    0.74
    an
    0.71
    k
    0.71
    Activations Density 0.000%

    No Known Activations