© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166412
    Prev
    Next
    INDEX
    Explanations

    `(` followed by `which` or `This`

    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_31_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
    ARA
    0.36
    Star
    0.35
    驿
    0.35
    Mount
    0.34
    싼
    0.34
    Road
    0.33
    되었다
    0.33
    매
    0.33
    ec
    0.33
    site
    0.33
    POSITIVE LOGITS
    梯度
    0.38
    ুলি
    0.37
    碚
    0.37
    ێکی
    0.37
     COORDIN
    0.37
     அதிகரி
    0.36
     tẩy
    0.36
    屓
    0.36
     vaisse
    0.35
    Tone
    0.35
    Activations Density 0.010%

    No Known Activations