© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81019
    Prev
    Next
    INDEX
    Explanations

    Night

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    Gir
    0.40
    OrderId
    0.39
     Gir
    0.37
    Жи
    0.37
    Cricket
    0.37
    quoia
    0.37
    𝚒
    0.37
    Newton
    0.36
    Gert
    0.36
     Rite
    0.35
    POSITIVE LOGITS
    CheckingType
    0.44
    ುದ
    0.43
    (":")[
    0.37
     sopr
    0.36
     Helsing
    0.36
    ভাগ
    0.35
     prüfe
    0.35
    kins
    0.35
     torpedo
    0.34
    ﻬ
    0.34
    Activations Density 0.002%

    No Known Activations