© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229378
    Prev
    Next
    INDEX
    Explanations

    know

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    它
    0.64
     it
    0.51
    Ι
    0.50
     它
    0.50
    ມັນ
    0.50
     It
    0.49
    𝘐
    0.47
    الإ
    0.45
    It
    0.45
     оно
    0.45
    POSITIVE LOGITS
    Cline
    0.42
    ल्ल्या
    0.40
     Shum
    0.39
    annam
    0.38
    levelname
    0.37
    matory
    0.37
    inse
    0.36
     秦
    0.36
    dot
    0.36
     couvrir
    0.36
    Activations Density 0.000%

    No Known Activations