© 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
    2. Gemma-3-27B-IT
    3. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 228617
    Prev
    Next
    INDEX
    Explanations

    mother health asi

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    },-\
    0.35
     pillows
    0.35
     glPushMatrix
    0.34
     પડી
    0.33
    畨
    0.33
     intersect
    0.33
    𒌍
    0.32
    接触
    0.32
    zyma
    0.32
    शियल
    0.32
    POSITIVE LOGITS
     ku
    0.48
     Ku
    0.40
     subdivision
    0.40
    dam
    0.39
    anger
    0.36
    onzo
    0.36
    scene
    0.36
     offense
    0.36
    varage
    0.36
    ku
    0.35
    Activations Density 0.000%

    No Known Activations