© 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. 7321
    Prev
    Next
    INDEX
    Explanations

    svg namespace url

    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
    습니다
    1.31
    적인
    1.26
    e
    1.26
     wk
    1.24
    EROS
    1.18
    llllllll
    1.18
    ४
    1.18
    ので
    1.16
    HPLC
    1.15
     indem
    1.13
    POSITIVE LOGITS
    т
    1.58
    د
    1.48
    ும்பி
    1.19
    वन
    1.18
    ಯ
    1.16
    я
    1.16
    ൽ
    1.14
    𝕝
    1.13
    ల్
    1.13
    selling
    1.12
    Activations Density 0.006%

    No Known Activations