© 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. 8205
    Prev
    Next
    INDEX
    Explanations

    disinfect, sanitize, infection

    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
    不會
    1.58
    𝒅
    1.56
    Ни
    1.53
    𝕐
    1.52
    不满
    1.50
     baryons
    1.42
    𝕆
    1.42
    teen
    1.42
    Р
    1.41
     ylab
    1.41
    POSITIVE LOGITS
    fon
    1.41
    म
    1.41
    ات
    1.40
    arote
    1.39
    aki
    1.36
    ار
    1.32
    isatie
    1.30
    }$
    1.29
    }=$
    1.25
     purport
    1.25
    Activations Density 0.057%

    No Known Activations