© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205786
    Prev
    Next
    INDEX
    Explanations

    clothing fit and style details

    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_37_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
    ፆ
    0.43
    ptăm
    0.38
    cliffe
    0.37
     जनप्रतिनि
    0.37
     Sagar
    0.37
    phi
    0.36
     まま
    0.36
    prob
    0.35
     Aki
    0.35
     coastline
    0.35
    POSITIVE LOGITS
    frameNStart
    0.38
    $/
    0.38
    egd
    0.38
     Framing
    0.38
    ড়যন্ত্র
    0.38
     framing
    0.37
    设计
    0.36
    遇到
    0.36
    Fram
    0.36
    WD
    0.35
    Activations Density 0.001%

    No Known Activations