© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117890
    Prev
    Next
    INDEX
    Explanations

    2022, 2023, 2000s, 1970, 1967

    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_27_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
     prophecies
    0.36
     complexity
    0.36
    {|\
    0.35
     počas
    0.34
     sentido
    0.33
     senso
    0.33
     complexities
    0.33
    㖦
    0.33
     voices
    0.33
    الل
    0.32
    POSITIVE LOGITS
    assador
    0.38
     removed
    0.35
     finalized
    0.32
     Clinical
    0.30
     Initially
    0.30
     Mitigation
    0.30
    之所以
    0.30
     ignoreString
    0.30
     สาว
    0.30
     консу
    0.29
    Activations Density 0.000%

    No Known Activations