© 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. 157897
    Prev
    Next
    INDEX
    Explanations

    awe-inspiring spectacle

    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
    n
    1.35
    :
    1.35
    i
    1.27
    ot
    1.19
    ir
    1.19
    or
    1.16
    at
    1.15
    im
    1.14
    ia
    1.14
    it
    1.13
    POSITIVE LOGITS
    1.25
    ␊
    1.09
     additives
    1.05
    ﻡ
    1.04
    ों
    1.03
     prohibitions
    1.02
     enzimas
    1.00
    ের
    0.99
     eloquence
    0.99
     surpluses
    0.98
    Activations Density 0.000%

    No Known Activations