© 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. 7795
    Prev
    Next
    INDEX
    Explanations

    www links

    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
    an
    0.81
    য়ের
    0.69
    el
    0.67
    es
    0.64
    w
    0.62
    বারের
    0.60
     tenuous
    0.60
    મ
    0.60
    ங்கிணை
    0.60
     spezielle
    0.60
    POSITIVE LOGITS
    𝘁
    0.97
    𝗴
    0.78
    𝗽
    0.74
    Т
    0.74
    Д
    0.73
     stderr
    0.72
    𝘀
    0.71
    𝗯
    0.70
     इसके
    0.69
     Siri
    0.69
    Activations Density 0.076%

    No Known Activations