© 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. 8380
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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
    ።
    1.63
     уж
    1.50
    اری
    1.44
    ﺯ
    1.44
    𒀭
    1.42
    ring
    1.40
    itions
    1.36
     quas
    1.36
    اتی
    1.35
    ה
    1.35
    POSITIVE LOGITS
    ূট
    2.00
    い
    1.58
    প
    1.58
    hn
    1.53
     linestyle
    1.50
    jó
    1.49
    ikul
    1.49
    rv
    1.48
    り
    1.46
    ಬ್ಬಿಣ
    1.46
    Activations Density 0.026%

    No Known Activations