© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132271
    Prev
    Next
    INDEX
    Explanations

    root

    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_50_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
    Champ
    0.46
    睗
    0.42
    bö
    0.41
     Ketch
    0.38
    akaranam
    0.38
    avatth
    0.38
     begins
    0.37
     Kef
    0.36
    champ
    0.36
    ፓ
    0.36
    POSITIVE LOGITS
    aban
    0.47
     Casas
    0.42
    ressa
    0.38
    emus
    0.38
     استح
    0.38
    संद
    0.38
     கை
    0.38
    E
    0.37
    镇
    0.37
    arness
    0.36
    Activations Density 0.000%

    No Known Activations