© 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. 12298
    Prev
    Next
    INDEX
    Explanations

    isotopes and isotopic composition

    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
    vedad
    0.40
    ńca
    0.40
     Gingerbread
    0.39
    inan
    0.36
    ರ್
    0.35
     плана
    0.35
    拎
    0.35
    掌
    0.35
    omorphism
    0.34
    延長
    0.34
    POSITIVE LOGITS
     isotope
    2.27
     isot
    2.08
     isotopes
    2.06
     isotopic
    2.03
     Isot
    2.03
    isotope
    1.84
    isotopes
    1.81
    isot
    1.63
     isotropic
    1.26
     isotropy
    1.02
    Activations Density 0.031%

    No Known Activations