© 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. 140305
    Prev
    Next
    INDEX
    Explanations

    conspiracy or occult

    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
     Dib
    0.38
     ചോദ്യ
    0.38
    elden
    0.38
    ⑭
    0.38
     pat
    0.37
    GDP
    0.37
    ड़िया
    0.37
    イルド
    0.37
     భూ
    0.36
    𝐳
    0.36
    POSITIVE LOGITS
    蜡
    0.37
     ralent
    0.36
    گے
    0.35
     oriented
    0.35
     suboptimal
    0.35
    쉴
    0.35
     encoded
    0.35
     privilegi
    0.35
     antennis
    0.34
    nipeg
    0.34
    Activations Density 0.000%

    No Known Activations