© 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. 229561
    Prev
    Next
    INDEX
    Explanations

    upward and downward trends

    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
    on
    1.28
    m
    1.09
    as
    1.00
    of
    0.93
    re
    0.93
    ’
    0.91
     njegov
    0.88
     pouze
    0.87
    it
    0.87
    r
    0.86
    POSITIVE LOGITS
    ை
    1.15
     an
    1.02
    ि
    1.02
    한
    0.93
    </h3>
    0.91
    л
    0.91
    گ
    0.89
    -
    0.88
    ა
    0.88
    ↵
    0.86
    Activations Density 0.000%

    No Known Activations