© 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-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241698
    Prev
    Next
    INDEX
    Explanations

    odd number check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    ovali
    0.46
    ahre
    0.43
    는다
    0.42
    ahs
    0.41
     Otro
    0.40
    粨
    0.40
     goomba
    0.40
    ilä
    0.39
    જરા
    0.38
    ĥ
    0.38
    POSITIVE LOGITS
    בר
    0.37
     سلسلة
    0.35
     التف
    0.34
    Categor
    0.34
    咆
    0.34
     verhaal
    0.34
     vehement
    0.34
     loopholes
    0.34
     implementation
    0.33
     requirement
    0.33
    Activations Density 0.002%

    No Known Activations