© 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. 6458
    Prev
    Next
    INDEX
    Explanations

    software patch updates

    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
    𝐠
    2.42
    স
    2.23
     cujo
    2.23
     ópt
    2.23
    forma
    2.18
    𝐯
    2.17
    𝐜
    2.16
    ver
    2.11
    いう
    2.10
    bcc
    2.09
    POSITIVE LOGITS
    वादी
    2.89
    ுள்ளார்
    2.83
    cvtColor
    2.64
    🅘
    2.60
    ुस्तान
    2.58
     flanges
    2.54
    ுள்ளனர்
    2.54
    вання
    2.38
    ка
    2.33
    鸯
    2.32
    Activations Density 0.055%

    No Known Activations