© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6407
    Prev
    Next
    INDEX
    Explanations

    jetpack compose

    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
    ी
    2.80
     जिस
    2.50
     haberse
    2.32
     Är
    2.32
    ad
    2.26
     Tatsache
    2.26
    +}
    2.26
     reel
    2.26
     lugar
    2.26
     oxidación
    2.25
    POSITIVE LOGITS
    arounds
    2.64
    fulness
    2.51
    檛
    2.38
    faction
    2.30
    ع
    2.22
    ר
    2.14
     Okada
    2.14
    zaam
    2.11
    ுகளை
    2.08
    ologies
    2.06
    Activations Density 0.001%

    No Known Activations