© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80417
    Prev
    Next
    INDEX
    Explanations

    compound interest calculation

    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_31_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
     Surve
    0.39
    ︹
    0.38
     june
    0.38
    माता
    0.37
     satur
    0.37
     opacity
    0.36
    Ensure
    0.36
     organic
    0.36
     ublox
    0.36
     oph
    0.36
    POSITIVE LOGITS
     UTF
    0.44
    UTF
    0.41
     hybridization
    0.40
     comprehensively
    0.39
     redistributed
    0.39
    }}=
    0.38
    }}=\
    0.38
    uti
    0.37
    utf
    0.37
    ayant
    0.37
    Activations Density 0.000%

    No Known Activations