© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261383
    Prev
    Next
    INDEX
    Explanations

    calibre or caliber

    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_5_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
    '
    1.45
    ní
    1.29
    ade
    1.23
     အ
    1.23
    리
    1.23
     for
    1.17
    သာ
    1.16
    ay
    1.13
    撅
    1.12
    lies
    1.11
    POSITIVE LOGITS
    م
    1.25
    v
    1.12
    .)
    1.11
    .",
    1.04
    ని
    1.00
     $
    1.00
    อ
    1.00
     flashlight
    0.99
    но
    0.97
     millionaire
    0.97
    Activations Density 0.000%

    No Known Activations