© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79442
    Prev
    Next
    INDEX
    Explanations

    initials followed by punctuation

    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_31_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
    额
    0.29
     Beats
    0.28
     Combat
    0.26
     prét
    0.26
    Classpath
    0.26
     snapped
    0.25
    牍
    0.25
     City
    0.25
    Paths
    0.24
     scanned
    0.24
    POSITIVE LOGITS
    焖
    0.28
    tv
    0.26
     termo
    0.26
    "-
    0.25
     ഉപ
    0.25
     опреде
    0.25
    nth
    0.25
     fed
    0.25
     halloween
    0.25
    нт
    0.25
    Activations Density 0.000%

    No Known Activations