© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197739
    Prev
    Next
    INDEX
    Explanations

    status related to downloads or paths

    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_4_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
    describe
    0.53
     obrá
    0.50
     that
    0.48
    v
    0.47
    t
    0.47
     argparse
    0.46
    fs
    0.46
    abcdef
    0.45
    MANAG
    0.45
     to
    0.44
    POSITIVE LOGITS
     त्याच
    0.52
     वार
    0.50
    ］
    0.49
     गुणवत्ता
    0.49
     എന്നാൽ
    0.49
     встанов
    0.49
     ड
    0.48
     όταν
    0.48
     ट
    0.48
     مک
    0.48
    Activations Density 0.000%

    No Known Activations