© 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. 261329
    Prev
    Next
    INDEX
    Explanations

    León

    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
    8
    1.34
    to
    1.21
    1
    1.20
    3
    1.20
     a
    1.16
    6
    1.14
    9
    1.12
    7
    1.12
    مند
    1.05
    B
    1.02
    POSITIVE LOGITS
    r
    1.55
    ل
    1.55
     for
    1.51
    t
    1.50
    ر
    1.38
    ه
    1.36
    त
    1.33
    ع
    1.24
    ต
    1.24
    ט
    1.22
    Activations Density 0.000%

    No Known Activations