© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51472
    Prev
    Next
    INDEX
    Explanations

    the

    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_55_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
     arrived
    0.35
    ,]
    0.34
     Incident
    0.34
     Επι
    0.34
     برخور
    0.34
    Ṛ
    0.34
    ༌
    0.33
    രം
    0.33
    ществует
    0.33
    При
    0.33
    POSITIVE LOGITS
    formation
    0.39
     Baird
    0.38
     endings
    0.38
     landmarks
    0.36
     landmark
    0.36
     pundits
    0.36
     dating
    0.35
     formation
    0.35
     Halle
    0.35
    Formation
    0.35
    Activations Density 0.004%

    No Known Activations