© 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. 7755
    Prev
    Next
    INDEX
    Explanations

    award-winning

    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
    ر
    2.31
    ą
    1.59
    л
    1.57
    з
    1.56
    rą
    1.54
    jenigen
    1.53
    nya
    1.51
    र्थ
    1.51
    िस
    1.51
     schop
    1.50
    POSITIVE LOGITS
     borderRadius
    1.93
    >=</
    1.68
    }$
    1.67
    }$,
    1.67
    dn
    1.66
    tale
    1.58
    }">
    1.58
    ा
    1.54
    اا
    1.52
    >−</
    1.50
    Activations Density 0.001%

    No Known Activations