© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121770
    Prev
    Next
    INDEX
    Explanations

    best followed by suitable product or insight

    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_27_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
    camp
    0.47
    prove
    0.43
    jsce
    0.41
    Camp
    0.40
    @
    0.40
     campground
    0.39
     campsite
    0.39
     Campground
    0.39
    logo
    0.38
    За
    0.38
    POSITIVE LOGITS
    햅
    0.42
     Sense
    0.38
     Debye
    0.37
    %)$
    0.36
     Meine
    0.36
     درست
    0.35
    InCM
    0.35
     Takahashi
    0.35
     Perrin
    0.34
     thermodynam
    0.34
    Activations Density 0.002%

    No Known Activations