© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4784
    Prev
    Next
    INDEX
    Explanations

    language indicating denials, accusations, and statements of fact, particularly in a legal or political context.

    oai_token-act-pair · gemini-2.0-flash

    denial/admission

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    脚注の使い方
    -0.65
     noDo
    -0.62
    الحياه
    -0.58
     sessionFactory
    -0.58
    @[+][
    -0.54
    клопе
    -0.53
    runApp
    -0.52
    tagHelperRunner
    -0.51
     nahilalakip
    -0.49
     reCAPTCHA
    -0.49
    POSITIVE LOGITS
     being
    1.84
    being
    1.59
    Being
    1.48
     BEING
    1.38
     Being
    1.36
     having
    1.27
     étant
    1.21
     fiind
    1.15
    having
    1.10
     essere
    1.05
    Activations Density 1.792%

    No Known Activations