© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10289
    Prev
    Next
    INDEX
    Explanations

    words related to firearms and their mechanisms

    oai_token-act-pair · gemini-2.0-flash

    Guns/weapons or technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     laid
    -0.55
     rospy
    -0.47
    legte
    -0.44
     Phipps
    -0.44
    毯
    -0.43
    legt
    -0.43
    azza
    -0.43
     Ordens
    -0.43
    pile
    -0.43
     áll
    -0.43
    POSITIVE LOGITS
    tvguidetime
    0.57
     geox
    0.57
    InvalidProtocol
    0.57
     Efq
    0.56
     sputnik
    0.56
    ">//
    0.54
    {}{}
    0.54
     تانيه
    0.54
    лтамалар
    0.53
    קישורים
    0.52
    Activations Density 0.871%

    No Known Activations