© 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. 52626
    Prev
    Next
    INDEX
    Explanations

    processes

    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
    น
    0.57
     ке
    0.46
     har
    0.45
     sert
    0.43
     Sert
    0.43
    <0x98>
    0.43
     द
    0.41
     damping
    0.41
     dampen
    0.41
    ន
    0.40
    POSITIVE LOGITS
    쥐
    0.44
    autant
    0.40
    KL
    0.37
    ocl
    0.35
    biet
    0.35
    pipe
    0.35
     Hearst
    0.34
    جواب
    0.34
     kl
    0.34
    מים
    0.34
    Activations Density 0.004%

    No Known Activations