© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153014
    Prev
    Next
    INDEX
    Explanations

    to string()

    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_23_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
    ilea
    0.43
    '):
    0.39
    mo
    0.38
    listener
    0.38
     গা
    0.38
    fas
    0.37
    사람
    0.37
    蚵
    0.37
    shoe
    0.37
    ভাস
    0.36
    POSITIVE LOGITS
     revised
    0.46
     revisions
    0.44
     imprim
    0.44
     challenges
    0.40
     mantra
    0.40
     herald
    0.40
     Challenges
    0.40
     hedon
    0.40
     dissection
    0.39
     victor
    0.39
    Activations Density 0.000%

    No Known Activations