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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2899
    Prev
    Next
    INDEX
    Explanations

    consult with a qualified professional

    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_5_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
    да
    0.62
    )$-
    0.59
    峠
    0.58
     puri
    0.56
    ки
    0.56
     differentiable
    0.55
     ensuing
    0.55
    оне
    0.55
    onego
    0.55
    ður
    0.54
    POSITIVE LOGITS
     hydrogens
    0.59
    ahre
    0.56
    ⁡</
    0.54
     quantifier
    0.52
    explode
    0.51
     средств
    0.51
    楷
    0.51
    Yea
    0.50
    >[</
    0.50
    擒
    0.50
    Activations Density 0.010%

    No Known Activations