© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107215
    Prev
    Next
    INDEX
    Explanations

    newline characters

    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_2_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
    r
    1.70
    the
    1.48
    an
    1.33
    .
    1.33
    la
    1.19
    و
    1.19
    م
    1.16
    ed
    1.16
    ре
    1.14
    ।
    1.13
    POSITIVE LOGITS
    ０
    1.39
    0
    1.33
    ۰
    1.32
     gewoon
    1.10
    ០
    1.10
    𝟎
    1.09
    𝟬
    1.06
    ૦
    1.05
    ০
    1.04
     سي
    1.02
    Activations Density 0.002%

    No Known Activations