© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163731
    Prev
    Next
    INDEX
    Explanations

    financial health indicators

    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
     reconciled
    0.40
    Index
    0.39
    '[
    0.38
    Economics
    0.38
     reconc
    0.37
    Pull
    0.37
    Semantic
    0.37
    Swim
    0.36
     startIndex
    0.35
    Flat
    0.35
    POSITIVE LOGITS
    iffe
    0.34
    த்ய
    0.34
    elly
    0.33
     laborer
    0.33
    ᾶ
    0.33
    boru
    0.33
     parle
    0.32
     revient
    0.32
     Montage
    0.32
    avax
    0.32
    Activations Density 0.002%

    No Known Activations