© 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. 53622
    Prev
    Next
    INDEX
    Explanations

    reducing parameters

    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
    తంగా
    0.45
    rocery
    0.40
    щаются
    0.38
     importantly
    0.38
    주
    0.37
     zab
    0.35
     desirous
    0.35
     주
    0.35
    க்கொண்டு
    0.35
     Lessor
    0.35
    POSITIVE LOGITS
    வாய
    0.37
     pelang
    0.37
     evoked
    0.37
    看得
    0.37
    铨
    0.36
    jev
    0.35
    hei
    0.35
    mani
    0.34
    違反
    0.34
     NOM
    0.34
    Activations Density 0.007%

    No Known Activations