© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8840
    Prev
    Next
    INDEX
    Explanations

    [Header("...")]

    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
    an
    2.70
     adequ
    2.31
     peacetime
    2.29
    𝐚
    2.28
    gris
    2.26
    𝐁
    2.18
    𝐕
    2.18
    𝐠
    2.13
    ان
    2.08
    𝐧
    2.06
    POSITIVE LOGITS
    uyền
    1.66
    مة
    1.64
    나는
    1.56
    학
    1.56
    ناک
    1.54
    வு
    1.51
    сия
    1.49
     Considerations
    1.45
    躇
    1.42
     પસ
    1.41
    Activations Density 0.007%

    No Known Activations