© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13832
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that indicate causality

    oai_token-act-pair · gemini-2.0-flash

    negative consequences

    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
     ajudá
    -0.67
     rendering
    -0.65
     guiding
    -0.60
    affect
    -0.58
     lead
    -0.58
     hurt
    -0.58
     supporting
    -0.57
     generating
    -0.56
    supporting
    -0.55
     Guiding
    -0.55
    POSITIVE LOGITS
    InputTagHelper
    0.71
    ReusableCell
    0.70
    zystać
    0.66
    XmlAccessType
    0.66
     typelib
    0.66
    ComponentScan
    0.65
     opting
    0.65
    UpInside
    0.65
    StoryboardSegue
    0.64
    TagHelper
    0.63
    Activations Density 14.396%

    No Known Activations