© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46052
    Prev
    Next
    INDEX
    Explanations

    "1. Introduction" or section headers

    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_13_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
     Edit
    0.46
     Online
    0.42
     Personal
    0.40
     Portfolio
    0.40
     Benefits
    0.40
     Number
    0.39
    <0x0D>
    0.38
     Neuro
    0.37
     Entire
    0.37
     About
    0.37
    POSITIVE LOGITS
     substitutional
    0.41
     fonctionnement
    0.40
    productions
    0.40
     도시
    0.40
     명령
    0.38
    ोच्च
    0.38
    olja
    0.36
    0.36
    Duong
    0.36
    0.36
    Activations Density 0.004%

    No Known Activations