© 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. 6654
    Prev
    Next
    INDEX
    Explanations

    Validator classes

    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
     gis
    2.47
    en
    2.42
    े
    2.40
    ेश
    2.35
    ана
    2.29
    ations
    2.22
    িং
    2.20
    িগুণ
    2.20
     blevet
    2.19
     самом
    2.16
    POSITIVE LOGITS
    ক
    2.79
     ruins
    2.73
     inwon
    2.41
    ठ
    2.39
    ulously
    2.32
    mis
    2.28
    ϻ
    2.28
    posium
    2.28
    क
    2.22
    đ
    2.21
    Activations Density 0.000%

    No Known Activations