© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180049
    Prev
    Next
    INDEX
    Explanations

    Estado Novo

    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_24_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
    ান্স
    0.51
    Schemas
    0.44
    τ
    0.44
     acrobat
    0.42
    Reuters
    0.42
     такое
    0.42
    避
    0.42
     frantically
    0.41
    )-
    0.41
    ريح
    0.40
    POSITIVE LOGITS
     derivations
    0.43
    OLOG
    0.42
     wholesome
    0.41
     integ
    0.40
     integrative
    0.39
     outpouring
    0.39
    oz
    0.39
     derivation
    0.39
     Islam
    0.39
     HOM
    0.39
    Activations Density 0.000%

    No Known Activations