© 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. 41754
    Prev
    Next
    INDEX
    Explanations

    release rollout plan

    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
    w
    0.88
    ר
    0.82
    ار
    0.72
    р
    0.70
    INA
    0.70
    ری
    0.68
    m
    0.68
    \%
    0.66
    ित
    0.65
    ERE
    0.65
    POSITIVE LOGITS
    (
    0.87
     rollout
    0.71
    hender
    0.55
    multip
    0.55
    "
    0.55
     Its
    0.55
     rollback
    0.54
     It
    0.53
     Spect
    0.52
    **/
    0.51
    Activations Density 0.003%

    No Known Activations