© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199004
    Prev
    Next
    INDEX
    Explanations

    metal building systems

    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_12_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
     Andaman
    0.46
    म
    0.46
    𝐴
    0.46
    ﻴ
    0.44
    anggil
    0.44
    މ
    0.42
    تر
    0.41
    ārt
    0.41
     화
    0.41
    android
    0.40
    POSITIVE LOGITS
    褛
    0.50
    齙
    0.49
    χη
    0.46
     tentativo
    0.43
     erfolgreich
    0.42
    預
    0.42
    褸
    0.41
     bearer
    0.41
     preclude
    0.40
     draped
    0.40
    Activations Density 0.000%

    No Known Activations