© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34153
    Prev
    Next
    INDEX
    Explanations

    Pentagram / -imbus / -ium / -acles

    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_7_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
     at
    0.15
    喩
    0.12
     be
    0.12
     scorn
    0.12
     hideous
    0.12
     not
    0.12
     gruesome
    0.12
     surprising
    0.11
    紹介
    0.11
     two
    0.11
    POSITIVE LOGITS
    9
    0.20
    6
    0.20
    0
    0.18
    ים
    0.18
    us
    0.18
    7
    0.18
    8
    0.18
    3
    0.17
    am
    0.17
    ed
    0.16
    Activations Density 0.002%

    No Known Activations