© 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. 230561
    Prev
    Next
    INDEX
    Explanations

    wonder leading to questioning

    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
    )
    1.00
    ਰ
    0.95
     be
    0.93
    𝚎
    0.93
    2
    0.92
    טר
    0.91
    ской
    0.86
    𝗿
    0.86
    ным
    0.85
     an
    0.84
    POSITIVE LOGITS
    на
    1.40
    k
    1.06
    x
    1.06
    िन
    1.02
    é
    0.96
    uin
    0.95
    ना
    0.94
    iz
    0.94
    im
    0.91
    ad
    0.91
    Activations Density 0.000%

    No Known Activations