© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233980
    Prev
    Next
    INDEX
    Explanations

    performance schedules and dates

    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
    盅
    0.40
    ሱስ
    0.40
     Viv
    0.39
     orn
    0.38
     Buddh
    0.37
     enthr
    0.36
    Tales
    0.36
     Sidhu
    0.36
    ሥ
    0.36
     olen
    0.35
    POSITIVE LOGITS
     alimentare
    0.43
    地
    0.39
    בל
    0.38
    ITO
    0.37
    泡
    0.37
     utilizes
    0.37
     progressions
    0.37
    tral
    0.36
    TEM
    0.36
    navbarSupported
    0.36
    Activations Density 0.000%

    No Known Activations