© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205808
    Prev
    Next
    INDEX
    Explanations

    Steve followed by famous names

    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_37_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
     erc
    0.40
    皐
    0.37
     Tw
    0.37
     dul
    0.36
    தியில்
    0.36
     atend
    0.36
     councillor
    0.36
    ាំ
    0.36
     Remembrance
    0.35
     त
    0.35
    POSITIVE LOGITS
     Zuge
    0.42
     केसांना
    0.40
    溃
    0.39
     کوڈ
    0.38
     כא
    0.38
    μφ
    0.38
    ié
    0.37
    Helen
    0.37
    WindowEvent
    0.36
     क्वेश्चन
    0.36
    Activations Density 0.000%

    No Known Activations