© 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. 7306
    Prev
    Next
    INDEX
    Explanations

    constant of integration C

    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
     crystallinity
    2.03
    jLabel
    1.90
    اته
    1.86
    antial
    1.82
    stuffs
    1.80
    ⎝
    1.76
    ,\,
    1.76
    তম
    1.76
     waahanga
    1.71
    analytics
    1.70
    POSITIVE LOGITS
    다
    2.18
    tering
    2.12
     entram
    2.09
     rikt
    1.97
     dichotomy
    1.89
    ма
    1.88
    ridden
    1.86
     permittivity
    1.86
     nourish
    1.84
    п
    1.83
    Activations Density 0.002%

    No Known Activations