© 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. 7327
    Prev
    Next
    INDEX
    Explanations

    interface and port

    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
    IEnumerable
    2.79
    ू
    2.56
    屜
    2.34
    joy
    2.25
     acre
    2.23
     Obwohl
    2.22
    dk
    2.17
     UserDefaults
    2.16
     spore
    2.14
     speck
    2.09
    POSITIVE LOGITS
    efeuille
    2.65
    тря
    2.53
    ਸ
    2.52
     negó
    2.46
    lož
    2.43
     lj
    2.40
    ်
    2.39
     nou
    2.38
    चीनी
    2.37
    љ
    2.36
    Activations Density 0.033%

    No Known Activations