© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104356
    Prev
    Next
    INDEX
    Explanations

    using programming keywords

    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_1_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
    ങ്ങൾ
    0.91
    ר
    0.90
    wright
    0.89
    were
    0.85
    km
    0.84
     Models
    0.84
    er
    0.82
    2
    0.81
    them
    0.81
    siniz
    0.80
    POSITIVE LOGITS
    在
    1.30
     in
    1.29
     في
    1.23
    t
    1.14
    a
    1.13
    ه
    1.13
    ت
    1.10
    ف
    1.10
    é
    1.09
    <bos>
    1.06
    Activations Density 0.000%

    No Known Activations