© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131093
    Prev
    Next
    INDEX
    Explanations

    Poshmark

    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
    ك
    1.10
    د
    1.06
    ف
    1.02
    ু
    1.01
    ב
    1.00
     modelos
    0.98
     at
    0.97
    س
    0.96
    י
    0.93
    डी
    0.91
    POSITIVE LOGITS
    that
    1.31
    nu
    1.00
    ların
    0.97
    ments
    0.97
    mask
    0.95
    mp
    0.95
    ndo
    0.94
    are
    0.93
    nia
    0.93
    nag
    0.92
    Activations Density 0.000%

    No Known Activations