© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12442
    Prev
    Next
    INDEX
    Explanations

    descriptions of violence, weaponry and death

    oai_token-act-pair · gemini-2.0-flash

    Violence/shooting/war

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dealing
    -0.85
     deal
    -0.84
     dealt
    -0.84
     AttributeSet
    -0.83
     deals
    -0.80
     Dealing
    -0.78
     Deal
    -0.77
    dealing
    -0.77
    Deal
    -0.76
     bullet
    -0.72
    POSITIVE LOGITS
     صوتيه
    0.65
     الحره
    0.60
    multer
    0.46
    دانشنامهٔ
    0.46
    ród
    0.46
     estimés
    0.46
     Unburied
    0.45
     גב
    0.44
    Bucks
    0.44
     disponibilités
    0.44
    Activations Density 3.596%

    No Known Activations