© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175287
    Prev
    Next
    INDEX
    Explanations

    gene alleles like A1, A2

    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_20_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
     ligado
    0.48
    蒈
    0.44
    Portale
    0.42
     الناتج
    0.42
     ligados
    0.40
    🧍
    0.39
     biología
    0.39
     Bisby
    0.39
    خراج
    0.39
    OscInitStruct
    0.38
    POSITIVE LOGITS
    suggest
    0.38
    locks
    0.38
     п
    0.37
     speaks
    0.37
     —
    0.36
     FFT
    0.36
    speak
    0.36
     Institutional
    0.36
     rations
    0.35
    dec
    0.35
    Activations Density 0.000%

    No Known Activations