© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34706
    Prev
    Next
    INDEX
    Explanations

    generating creative content

    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_31_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
     accepts
    0.38
     Chaplin
    0.37
    浆
    0.36
     disrupts
    0.36
     tolerate
    0.35
     모든
    0.35
     pulls
    0.34
    plication
    0.34
     siRNA
    0.34
     accepter
    0.34
    POSITIVE LOGITS
    }}{{
    0.38
     ጥ
    0.37
     اٹھ
    0.37
    পথ
    0.36
    reath
    0.35
     succession
    0.35
     rusty
    0.34
    。",
    0.34
     시설
    0.34
     やつ
    0.33
    Activations Density 0.000%

    No Known Activations