© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140704
    Prev
    Next
    INDEX
    Explanations

    overcoming difficulty

    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_46_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
     Degrees
    0.38
    వ్వు
    0.38
    udian
    0.38
    }°
    0.37
     دین
    0.36
    〝
    0.36
     deg
    0.36
     Jno
    0.36
     degrees
    0.35
     Winfrey
    0.35
    POSITIVE LOGITS
     avanzados
    0.45
    ান্দ
    0.44
    觀
    0.42
    bok
    0.42
     Advanced
    0.38
     ($_
    0.38
     Vocabulary
    0.38
     darts
    0.37
    ektor
    0.37
    gx
    0.37
    Activations Density 0.027%

    No Known Activations