© 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. 7271
    Prev
    Next
    INDEX
    Explanations

    php function definition

    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
    에
    1.43
    b
    1.38
    ter
    1.29
    tanto
    1.27
    되는
    1.18
    pronged
    1.13
    과
    1.12
    ll
    1.12
    lle
    1.09
    aneous
    1.09
    POSITIVE LOGITS
    𝙞
    1.67
    िक
    1.62
    𝙣
    1.47
    𝙖
    1.46
     Xét
    1.40
     Также
    1.40
    ⁄
    1.39
     retractable
    1.38
    𝙋
    1.36
     Ты
    1.34
    Activations Density 0.000%

    No Known Activations