© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48681
    Prev
    Next
    INDEX
    Explanations

    telling stories

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    alliative
    0.39
    lerim
    0.38
     psychologically
    0.38
     tectonic
    0.38
     karm
    0.37
    }}]
    0.37
     animasi
    0.36
    埗
    0.36
    OrderFlight
    0.36
    映像
    0.36
    POSITIVE LOGITS
     games
    0.47
     blueberry
    0.46
     treats
    0.44
     mud
    0.44
     chases
    0.42
     umbrella
    0.41
     mischief
    0.40
     tink
    0.40
    追
    0.40
     FIELDS
    0.39
    Activations Density 0.027%

    No Known Activations