© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16189
    Prev
    Next
    INDEX
    Explanations

    Lifeline: Suicide & Crisis

    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_40_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
     Designing
    0.38
    ㄎ
    0.35
    নিবেশ
    0.35
    㖮
    0.35
     Producing
    0.34
    σης
    0.33
     Client
    0.33
     клиент
    0.33
    etok
    0.33
    client
    0.32
    POSITIVE LOGITS
     형
    0.41
     зада
    0.35
     ক্যাম্পে
    0.34
    MIUM
    0.34
    में
    0.33
    odian
    0.33
     valg
    0.33
     درخت
    0.33
     felonies
    0.33
    一度
    0.33
    Activations Density 0.005%

    No Known Activations