© 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. 160943
    Prev
    Next
    INDEX
    Explanations

    staggering stride

    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
    ﻚ
    1.29
    ﺬ
    1.08
     informes
    1.05
     bailar
    1.05
    ﻄ
    1.02
    야
    1.01
    ﺍ
    1.01
    ﻦ
    1.01
    ﻱ
    1.01
    いろんな
    1.00
    POSITIVE LOGITS
    of
    1.68
    with
    1.13
    ز
    1.13
    이었
    1.10
    p
    1.09
    ت
    1.09
    ة
    1.08
    ad
    1.07
    was
    1.05
    ých
    1.03
    Activations Density 0.000%

    No Known Activations