© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236990
    Prev
    Next
    INDEX
    Explanations

    instructions, safety, installation, translations, gas

    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_32_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
    Browse
    0.38
    helia
    0.36
     Browse
    0.36
    摔
    0.36
    척
    0.35
     jointly
    0.35
    Boost
    0.34
    ❒
    0.34
     dice
    0.34
    ρή
    0.34
    POSITIVE LOGITS
     pope
    0.45
     habit
    0.44
     Tink
    0.41
     ਦਵਾਈ
    0.41
     Habit
    0.41
     creek
    0.40
     ఇంత
    0.40
     disgr
    0.38
    habit
    0.38
     fabricante
    0.38
    Activations Density 0.000%

    No Known Activations