© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15779
    Prev
    Next
    INDEX
    Explanations

    salary ranges: $xxk - $yyk

    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
    不超过
    0.43
     republika
    0.40
     среднем
    0.40
    muy
    0.38
    睗
    0.38
     Malta
    0.36
    స్క
    0.36
     stazione
    0.36
    Lm
    0.36
     primos
    0.36
    POSITIVE LOGITS
     widening
    0.37
    이트
    0.35
    totals
    0.34
    GetInt
    0.33
    총
    0.33
    힘
    0.32
     कुल
    0.32
     broadening
    0.32
     looping
    0.32
     Deal
    0.32
    Activations Density 0.003%

    No Known Activations