© 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. 8296
    Prev
    Next
    INDEX
    Explanations

    II, III, class

    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
     kendisine
    2.13
     skall
    1.99
    োহণ
    1.93
    agt
    1.89
     garis
    1.84
    優
    1.78
    È
    1.78
     duidelijk
    1.75
    গত
    1.75
     zaw
    1.71
    POSITIVE LOGITS
    <0x80>
    2.17
    ᵛ
    1.89
    <sup>
    1.87
     mancan
    1.81
    weds
    1.77
     metų
    1.70
    াকা
    1.68
    te
    1.67
    ﻢ
    1.67
     beamed
    1.63
    Activations Density 0.008%

    No Known Activations