© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5680
    Prev
    Next
    INDEX
    Explanations

    Khyber Pakhtunkhwa

    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
    ال
    0.81
    unable
    0.81
    শীল
    0.79
     dicha
    0.79
    𝙋
    0.78
    }$:
    0.78
     able
    0.77
     supon
    0.77
    ো
    0.77
     disseminating
    0.75
    POSITIVE LOGITS
    script
    0.80
    dis
    0.79
    𖥔
    0.78
    dens
    0.76
     instar
    0.75
    dip
    0.75
    vindo
    0.72
    น
    0.72
    sprecher
    0.72
    nummer
    0.71
    Activations Density 0.003%

    No Known Activations