© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1789
    Prev
    Next
    INDEX
    Explanations

    angular component.ts

    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_39_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
    ﻃ
    0.21
    ⁣
    0.21
     CCM
    0.21
     aspirated
    0.20
     recipe
    0.20
     physics
    0.20
     scream
    0.20
    taskId
    0.20
     gew
    0.19
     Cartan
    0.19
    POSITIVE LOGITS
    現金
    0.17
     yeniden
    0.17
     Ё
    0.16
     Ksh
    0.16
    volved
    0.16
    voirs
    0.16
    ydat
    0.16
    郧
    0.16
    escence
    0.16
    ләре
    0.16
    Activations Density 0.000%

    No Known Activations