© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130079
    Prev
    Next
    INDEX
    Explanations

    return value

    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_25_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
     ruthless
    0.37
     subcontract
    0.37
     hooking
    0.37
     ingenious
    0.36
    狐
    0.35
     thriving
    0.35
     initiating
    0.35
    这件事
    0.35
     തുടങ്ങി
    0.34
    这一
    0.34
    POSITIVE LOGITS
    肱
    0.37
     tally
    0.36
     Sele
    0.35
     yere
    0.34
    ັງ
    0.33
    ãn
    0.32
     memb
    0.32
     pagar
    0.32
    ounced
    0.32
     Sed
    0.32
    Activations Density 0.006%

    No Known Activations