© 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. 8589
    Prev
    Next
    INDEX
    Explanations

    please specify, confirm, move

    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
    ר
    1.72
     нада
    1.70
    ,{\
    1.46
     accountable
    1.45
    нке
    1.41
    ories
    1.41
    ار
    1.37
    <0x80>
    1.36
    ত
    1.31
     Бүген
    1.31
    POSITIVE LOGITS
    िक
    1.65
    clearInterval
    1.65
     overtaking
    1.56
    fashioned
    1.52
    ને
    1.52
    charset
    1.52
    natured
    1.49
    🅐
    1.47
    ia
    1.45
    $-
    1.45
    Activations Density 0.042%

    No Known Activations