© 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. 41566
    Prev
    Next
    INDEX
    Explanations

    ready-made

    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
    '
    0.78
    ing
    0.77
    ;
    0.75
    ig
    0.72
     salicylate
    0.66
     τόσο
    0.60
     polymerase
    0.59
     seminal
    0.59
    iv
    0.58
     ablation
    0.56
    POSITIVE LOGITS
    ש
    0.89
    т
    0.86
    с
    0.86
    س
    0.84
    V
    0.82
    দের
    0.79
    يل
    0.79
    ک
    0.79
    ет
    0.79
    ت
    0.78
    Activations Density 0.001%

    No Known Activations