© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212340
    Prev
    Next
    INDEX
    Explanations

    plus

    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_5_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
    ación
    1.41
    u
    1.40
    يا
    1.26
    of
    1.23
    on
    1.22
    '
    1.20
    in
    1.08
    ing
    1.05
    ação
    1.02
    inę
    0.97
    POSITIVE LOGITS
    ни
    1.19
    ๑
    1.16
    c
    1.15
    வில்லை
    1.09
     BEEN
    1.07
    ש
    1.07
     can
    1.04
     ibid
    1.01
     rozpoczę
    1.00
    }.
    0.99
    Activations Density 0.001%

    No Known Activations