© 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. 8652
    Prev
    Next
    INDEX
    Explanations

    blunt instrument

    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
    אה
    2.74
    которые
    2.57
     obtient
    2.45
    an
    2.39
    gradle
    2.38
    麽
    2.33
     pensar
    2.27
    િંગ
    2.26
    できます
    2.24
    띈
    2.16
    POSITIVE LOGITS
    а
    2.84
    ்த்து
    2.70
    providecommand
    2.48
    ንዳንድ
    2.47
    यानक
    2.42
     heir
    2.37
     demean
    2.25
     aki
    2.25
     fluttering
    2.24
    quiera
    2.23
    Activations Density 0.000%

    No Known Activations