© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32209
    Prev
    Next
    INDEX
    Explanations

    political purges and paranoia

    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_31_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
    츨
    0.39
     배열
    0.39
    쪽
    0.38
     TAE
    0.38
    எல்
    0.36
    భవ
    0.36
    激素
    0.35
     distributive
    0.35
    రిత్ర
    0.35
    クラブ
    0.35
    POSITIVE LOGITS
    ocatore
    0.41
    atherine
    0.39
    otyping
    0.36
    🧖
    0.36
     paranoid
    0.35
     purge
    0.34
    AO
    0.34
     informant
    0.34
    workflows
    0.33
     paranoia
    0.33
    Activations Density 0.027%

    No Known Activations