© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 70
    Prev
    Next
    INDEX
    Explanations

    words related to international incidents, politics, and government

    oai_token-act-pair · gemini-2.0-flash

    Resignations and terminations

    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
    Porque
    -0.58
     following
    -0.58
    Following
    -0.57
     Following
    -0.56
    hoppers
    -0.54
    following
    -0.52
    karena
    -0.51
     Because
    -0.50
    Because
    -0.49
    ONSORED
    -0.48
    POSITIVE LOGITS
    AndEndTag
    0.76
    RenderAtEndOf
    0.69
    ConstraintMaker
    0.68
     '{@
    0.61
     للاسماء
    0.60
    MessageOf
    0.59
     بيها
    0.59
     المعيارى
    0.58
    DrawerToggle
    0.56
    !("{
    0.54
    Activations Density 19.083%

    No Known Activations