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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 78230
    Prev
    Next
    INDEX
    Explanations

    add\_action or define environment

    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_31_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
     ace
    0.41
    湾
    0.39
     PHYSICAL
    0.39
     physical
    0.38
     matematik
    0.38
     fysis
    0.37
     gyms
    0.36
    తున్నారు
    0.36
    cols
    0.36
    世
    0.36
    POSITIVE LOGITS
    RCB
    0.38
     CTCF
    0.36
     রোগ
    0.35
     Villiers
    0.35
    }_{-
    0.35
     Decreto
    0.34
    億円
    0.34
     CQL
    0.34
    的存在
    0.33
    beard
    0.33
    Activations Density 0.000%

    No Known Activations