© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86237
    Prev
    Next
    INDEX
    Explanations

    ID and related fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    вена
    0.44
    hentication
    0.44
    姮
    0.41
     책임
    0.38
     હે
    0.36
     Venezia
    0.36
     bragging
    0.36
     Alejandra
    0.35
    펙
    0.35
     Venice
    0.35
    POSITIVE LOGITS
     swiftly
    0.45
    ----------------
    0.43
    三
    0.42
     swift
    0.40
     accordingly
    0.40
     litigation
    0.39
     اللهم
    0.39
    遷
    0.39
    ซ์
    0.39
    citep
    0.38
    Activations Density 0.001%

    No Known Activations