© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198652
    Prev
    Next
    INDEX
    Explanations

    then + descriptive phrase

    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_15_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
     polygons
    0.34
     lambda
    0.34
     poking
    0.34
     tastings
    0.33
    ળે
    0.32
     mineralization
    0.32
    ᖕ
    0.32
    وون
    0.31
     resampling
    0.31
     disinfecting
    0.31
    POSITIVE LOGITS
    t
    0.46
    circa
    0.40
    (
    0.38
    }}
    0.34
     Ot
    0.33
    |
    0.32
     attuale
    0.32
     appunto
    0.32
    tube
    0.31
    Ch
    0.31
    Activations Density 0.002%

    No Known Activations