© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109946
    Prev
    Next
    INDEX
    Explanations

    analyzes

    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_2_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
    a
    1.43
    '
    1.30
    া
    1.16
    et
    1.05
    el
    1.02
    вав
    0.98
    0
    0.98
    нда
    0.96
     by
    0.96
    це
    0.96
    POSITIVE LOGITS
     (
    1.23
     is
    1.13
    ل
    1.12
    }(
    1.05
    ম
    1.04
    }!
    0.97
     因为
    0.93
    ব
    0.90
    ssä
    0.88
    ט
    0.87
    Activations Density 0.000%

    No Known Activations