© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53785
    Prev
    Next
    INDEX
    Explanations

    regex or pattern

    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_30_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
     algorithm
    0.19
     emper
    0.18
     algorithms
    0.18
     phen
    0.17
    **************
    0.17
     professor
    0.17
     strategies
    0.16
     થયો
    0.16
    见过
    0.16
     cyclic
    0.16
    POSITIVE LOGITS
    醯
    0.19
    ucalyptus
    0.18
    ∥
    0.18
     voorzien
    0.17
    Catalogue
    0.17
    AY
    0.17
    sup
    0.17
    achs
    0.16
     ésta
    0.16
    dome
    0.16
    Activations Density 0.000%

    No Known Activations