© 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. 8587
    Prev
    Next
    INDEX
    Explanations

    phrase "free of"

    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
    কর
    2.95
    router
    2.80
     pancreas
    2.70
    cknow
    2.67
     beetje
    2.62
     tým
    2.61
    𝘯
    2.55
    𝘴
    2.49
     hade
    2.45
    न
    2.43
    POSITIVE LOGITS
     النار
    2.43
    дна
    2.41
    hasta
    2.28
    е
    2.28
    t
    2.21
     Trotz
    2.21
    te
    2.19
     certeza
    2.18
     prazer
    2.18
    ála
    2.16
    Activations Density 0.031%

    No Known Activations