© 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. 234157
    Prev
    Next
    INDEX
    Explanations

    issues or concerns

    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
    nextDouble
    0.41
    renders
    0.41
    ánt
    0.40
    ﭔ
    0.40
    ifiant
    0.40
    izaci
    0.39
    amentos
    0.39
    Interruptions
    0.39
    ruption
    0.38
    ísica
    0.38
    POSITIVE LOGITS
    खे
    0.42
     품
    0.39
     Serious
    0.37
     barrier
    0.37
    ភ
    0.36
     sakin
    0.35
    훈
    0.35
     emp
    0.35
     करता
    0.35
     stable
    0.35
    Activations Density 0.004%

    No Known Activations