© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5491
    Prev
    Next
    INDEX
    Explanations

    Counter-terrorism and sending messages

    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_39_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
     Jharkhand
    0.43
    晰
    0.42
     παρα
    0.42
     झारखंड
    0.42
     Ranchi
    0.40
    ador
    0.38
     पटना
    0.38
     Agr
    0.37
    ঁ
    0.37
     بابا
    0.37
    POSITIVE LOGITS
    Dag
    0.61
     Dag
    0.58
    Dig
    0.46
    гъ
    0.45
     DAG
    0.44
     Dig
    0.43
     Ing
    0.42
     dag
    0.42
    Ing
    0.41
    Digest
    0.40
    Activations Density 0.018%

    No Known Activations