© 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. 3077
    Prev
    Next
    INDEX
    Explanations

    widget

    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
    талия
    1.92
    م
    1.72
    ad
    1.60
    ாக
    1.57
    গুলো
    1.55
    ко
    1.54
     quedarse
    1.50
    но
    1.50
    er
    1.47
    r
    1.46
    POSITIVE LOGITS
    UES
    1.90
     evil
    1.90
    ≌
    1.86
    ∽
    1.85
    盱
    1.82
    kms
    1.81
     sacraments
    1.79
    abhave
    1.79
     hyperfine
    1.78
     transmittance
    1.78
    Activations Density 0.000%

    No Known Activations