© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-TRANSCODER-262K
    4. 79833
    Prev
    Next
    INDEX
    Explanations

    Red

    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
     Garth
    0.42
    lambda
    0.36
    burn
    0.36
    |^{\
    0.35
    rich
    0.35
     literally
    0.35
    criminal
    0.34
    gym
    0.34
    ilden
    0.34
    delta
    0.33
    POSITIVE LOGITS
     वडील
    0.43
     tutaj
    0.40
     मता
    0.40
     pendapat
    0.40
    ňa
    0.39
    qda
    0.39
     FETCH
    0.39
    笕
    0.38
     TC
    0.38
     Tuc
    0.38
    Activations Density 0.000%

    No Known Activations