© 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
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 130167
    Prev
    Next
    INDEX
    Explanations

    videos

    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
     বা
    0.41
     conductance
    0.39
     ή
    0.39
     должно
    0.39
    探测
    0.38
     bypass
    0.37
     veya
    0.36
     или
    0.36
    ühren
    0.35
     Центра
    0.35
    POSITIVE LOGITS
    astă
    0.38
    :"
    0.37
    :""
    0.36
    :'
    0.36
     Conselho
    0.36
    AsAction
    0.35
     :"
    0.35
    Xd
    0.35
    Keeping
    0.35
     sessão
    0.35
    Activations Density 0.000%

    No Known Activations