© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83294
    Prev
    Next
    INDEX
    Explanations

    monolayer graphene

    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_0_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
    ل
    1.91
    ي
    1.66
    י
    1.47
    lj
    1.37
    ל
    1.32
    ت
    1.24
    Й
    1.24
    হ
    1.21
    ؟
    1.20
    Б
    1.18
    POSITIVE LOGITS
    1
    1.72
    en
    1.44
    g
    1.42
    ation
    1.41
    ach
    1.38
    ov
    1.34
    ers
    1.30
    ens
    1.30
    ate
    1.28
    ana
    1.28
    Activations Density 0.000%

    No Known Activations