© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141680
    Prev
    Next
    INDEX
    Explanations

    emergency fund months

    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_12_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
    АР
    0.52
    fähig
    0.50
    㕫
    0.47
     मृत
    0.46
    bike
    0.45
     RegExp
    0.45
     柄
    0.45
    蒡
    0.45
    bery
    0.44
    acinth
    0.44
    POSITIVE LOGITS
     savings
    0.63
     dover
    0.62
    ودي
    0.57
     voler
    0.55
     individuale
    0.54
              
    0.54
    savings
    0.54
     eradic
    0.53
     su
    0.52
     woo
    0.51
    Activations Density 0.001%

    No Known Activations