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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6606
    Prev
    Next
    INDEX
    Explanations

    question-starting words

    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
    ب
    3.48
    ে
    2.86
     možné
    2.62
    ו
    2.47
    وٹی
    2.43
    ه
    2.40
    ৭
    2.32
    ер
    2.30
     Ayrıca
    2.29
    ার্
    2.29
    POSITIVE LOGITS
     allé
    2.42
    ংকর
    2.39
    ἷ
    2.35
    я
    2.31
    ธ์
    2.26
    ്യം
    2.24
    стый
    2.23
     absurdity
    2.23
     thuật
    2.22
    ்ப்ப
    2.22
    Activations Density 0.000%

    No Known Activations