© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86537
    Prev
    Next
    INDEX
    Explanations

    in between

    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_3_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
    0.90
    aría
    0.77
    ur
    0.71
    2
    0.69
    er
    0.65
    é
    0.64
    ing
    0.63
    ë
    0.60
     ",
    0.60
     Wikipedia
    0.59
    POSITIVE LOGITS
    ון
    0.80
    ك
    0.80
    ৪
    0.77
    𝓢
    0.70
    ｽ
    0.67
    ｸ
    0.67
     tiempos
    0.66
    ខ្សែ
    0.65
    𝐅
    0.65
    𝟖
    0.64
    Activations Density 0.001%

    No Known Activations