© 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. 130747
    Prev
    Next
    INDEX
    Explanations

    app

    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
    per
    0.41
    elle
    0.41
    measurement
    0.40
    uar
    0.40
    ellar
    0.39
    য়ার
    0.38
    ਪ
    0.38
    erm
    0.38
    };
    0.38
    istor
    0.37
    POSITIVE LOGITS
     idioma
    0.42
     þei
    0.40
    /(:
    0.40
     famed
    0.39
    краё
    0.39
    брита
    0.39
    োডে
    0.38
    禮
    0.38
     organized
    0.38
     PACS
    0.38
    Activations Density 0.002%

    No Known Activations