© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18533
    Prev
    Next
    INDEX
    Explanations

    numbers like 12, 24

    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_40_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
    contained
    0.38
    नर
    0.33
     contained
    0.33
    csr
    0.33
    位
    0.32
    amanya
    0.32
    processed
    0.31
    हु
    0.31
    corpor
    0.31
    consulté
    0.31
    POSITIVE LOGITS
     Twelve
    0.64
     १२
    0.63
     ১২
    0.62
    Twelve
    0.61
    ১২
    0.56
     २४
    0.55
     बारह
    0.55
     १३
    0.53
     zwölf
    0.52
     ۱
    0.51
    Activations Density 0.047%

    No Known Activations