© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126333
    Prev
    Next
    INDEX
    Explanations

    indicator of value/performance

    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_37_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
    ้าว
    0.43
     countDown
    0.37
    ＰＥ
    0.37
     justifying
    0.36
    <unused14>
    0.35
    ochem
    0.35
    spinlock
    0.35
    阀
    0.35
    andet
    0.34
    ချ
    0.34
    POSITIVE LOGITS
     indication
    0.85
     indicator
    0.78
     indications
    0.78
     proxy
    0.77
     proxies
    0.77
     indicators
    0.76
     indicative
    0.75
     indik
    0.74
     reflects
    0.73
    反映
    0.71
    Activations Density 0.296%

    No Known Activations