© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9052
    Prev
    Next
    INDEX
    Explanations

    coding and software

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     সেল
    0.79
    夜
    0.72
    န္
    0.72
    ፨
    0.69
     multimodal
    0.68
     IOS
    0.68
     Atth
    0.67
    evším
    0.67
    žev
    0.67
     地域
    0.67
    POSITIVE LOGITS
     Architect
    0.74
    architect
    0.71
    Architect
    0.71
     architectural
    0.69
     architect
    0.68
    꽁
    0.68
     הפר
    0.66
     arquitect
    0.64
     تک
    0.63
     Garden
    0.62
    Activations Density 0.001%

    No Known Activations