© 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. 126189
    Prev
    Next
    INDEX
    Explanations

    methods, Studios, jail

    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
     a
    0.86
    )
    0.70
    л
    0.68
     illicit
    0.63
     probl
    0.63
     their
    0.61
     o
    0.61
     analy
    0.60
    ien
    0.59
     εικό
    0.58
    POSITIVE LOGITS
    ע
    0.89
    も
    0.80
    at
    0.77
    ना
    0.77
    اخت
    0.74
    اک
    0.74
    ിയ
    0.71
    ิ
    0.70
    ון
    0.66
    to
    0.65
    Activations Density 0.012%

    No Known Activations