© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33239
    Prev
    Next
    INDEX
    Explanations

    software libraries and frameworks

    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_31_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
    वीण
    0.26
     насыщен
    0.25
     वंश
    0.25
    bauen
    0.24
    溱
    0.24
    Valent
    0.23
    Mâc
    0.23
    瞽
    0.23
    Blurred
    0.23
     Concentrations
    0.23
    POSITIVE LOGITS
     flights
    0.29
     meets
    0.28
     anv
    0.28
     issues
    0.26
     introductory
    0.26
    /
    0.26
     interaction
    0.26
     business
    0.25
     true
    0.25
     lines
    0.25
    Activations Density 0.005%

    No Known Activations