© 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. 86467
    Prev
    Next
    INDEX
    Explanations

    across from

    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
    ↵
    0.95
    N
    0.80
    S
    0.71
    cando
    0.68
     불구하고
    0.68
    kadot
    0.67
    e
    0.65
    昱
    0.64
    bcrypt
    0.63
    prett
    0.61
    POSITIVE LOGITS
    of
    0.85
     över
    0.80
    ?
    0.79
     d
    0.78
     über
    0.75
     over
    0.71
    य
    0.69
     lavish
    0.68
     g
    0.66
    OWN
    0.65
    Activations Density 0.000%

    No Known Activations