© 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. 261429
    Prev
    Next
    INDEX
    Explanations

    Shaft, Shauni, Shaquille, Shaun

    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
    ０
    1.05
    to
    1.05
    <0x80>
    1.04
    arım
    1.00
    lardan
    1.00
    owane
    0.97
    稈
    0.94
    uje
    0.90
    این
    0.90
    oló
    0.90
    POSITIVE LOGITS
    9
    1.52
    5
    1.50
    ა
    1.48
    ست
    1.27
    ט
    1.24
    ()
    1.21
    6
    1.21
    ب
    1.20
    ס
    1.16
    ,
    1.07
    Activations Density 0.001%

    No Known Activations