© 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. 79936
    Prev
    Next
    INDEX
    Explanations

    gravitational

    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
    v
    1.76
    c
    1.44
    리
    1.36
    k
    1.32
    د
    1.32
    I
    1.20
    ien
    1.16
    기는
    1.11
    A
    1.11
    ના
    1.05
    POSITIVE LOGITS
    ר
    1.38
    ﻟ
    1.38
    ка
    1.30
    ătoare
    1.30
    of
    1.27
    то
    1.22
    ر
    1.21
    arı
    1.15
    ПУ
    1.15
    the
    1.13
    Activations Density 0.001%

    No Known Activations