© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13664
    Prev
    Next
    INDEX
    Explanations

    dolphin

    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_13_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
    磕
    0.50
    hami
    0.50
     হামিদ
    0.47
    আব
    0.46
    ಿಸುವ
    0.46
     짜
    0.46
    𝕜
    0.46
     uncoated
    0.46
    緩和
    0.46
     CPS
    0.45
    POSITIVE LOGITS
    r
    0.63
    t
    0.55
    l
    0.54
     মহারাজ
    0.52
    <0x0D>
    0.52
     conversa
    0.51
    v
    0.51
     gezegd
    0.49
     marts
    0.49
     municipio
    0.49
    Activations Density 0.001%

    No Known Activations