© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5142
    Prev
    Next
    INDEX
    Explanations

    consulting and advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
     dozen
    2.58
    ngthening
    2.57
     gange
    2.55
    addClass
    2.49
    ｭ
    2.49
     throne
    2.43
    capped
    2.43
    grilled
    2.41
    yearly
    2.33
     গঠিত
    2.33
    POSITIVE LOGITS
    ો
    2.56
    有一些
    2.27
    -\
    2.25
     nave
    2.24
    ní
    2.22
    ような
    2.12
    ~$
    2.11
     motivo
    2.11
    ຫາ
    2.10
     luego
    2.10
    Activations Density 0.048%

    No Known Activations