© 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. 6857
    Prev
    Next
    INDEX
    Explanations

    bless the [word]

    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
    ‒
    2.85
     malignancies
    2.66
     quantifier
    2.54
    ње
    2.53
    ه
    2.50
    isInt
    2.47
    썼
    2.47
    setTo
    2.44
    🧾
    2.41
    orElse
    2.40
    POSITIVE LOGITS
     trove
    2.82
    াউ
    2.70
    لي
    2.65
    полу
    2.65
    きて
    2.55
     telas
    2.53
    ش
    2.48
    rna
    2.46
     saj
    2.39
    り
    2.37
    Activations Density 0.014%

    No Known Activations