© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145504
    Prev
    Next
    INDEX
    Explanations

    proof

    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_0_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
    s
    2.05
    d
    1.64
    in
    1.63
    c
    1.53
    r
    1.47
    ik
    1.46
    z
    1.44
     in
    1.34
    ים
    1.34
    and
    1.28
    POSITIVE LOGITS
     as
    2.05
    오
    1.52
    어
    1.48
    </h3>
    1.34
    پی
    1.31
    のは
    1.30
    </h6>
    1.28
    وی
    1.27
    ер
    1.25
     가진
    1.25
    Activations Density 0.001%

    No Known Activations