© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 86734
    Prev
    Next
    INDEX
    Explanations

    parsing lines of text

    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_23_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
     ideologies
    0.51
     ideology
    0.45
    嬗
    0.44
    ById
    0.42
     indestruct
    0.42
     establishments
    0.41
    یثیت
    0.41
     filosof
    0.40
     construe
    0.40
     antidepressant
    0.40
    POSITIVE LOGITS
    Z
    0.39
    shot
    0.38
    KAL
    0.38
    роди
    0.37
    ρισ
    0.37
    romantic
    0.37
    H
    0.36
    arc
    0.36
     GLA
    0.36
    GL
    0.36
    Activations Density 0.003%

    No Known Activations