© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6234
    Prev
    Next
    INDEX
    Explanations

    phone numbers or how to contact someone

    oai_token-act-pair · gemini-2.0-flash

    programming terms and technical identifiers

    np_token-act-pair-logits · gpt-4o-mini

    Phone numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    RTHOOK
    -0.42
    latego
    -0.39
    Corpus
    -0.39
     Corpus
    -0.38
    ütün
    -0.36
     laying
    -0.35
    gesetz
    -0.35
     C
    -0.35
     במס
    -0.35
    ksessa
    -0.34
    POSITIVE LOGITS
    GraphicsUnit
    0.79
    WithIOException
    0.78
    StoryboardSegue
    0.75
     utafitiHapana
    0.69
     OnEnable
    0.68
    THISDAY
    0.66
    TargetException
    0.65
    Архівовано
    0.64
    Démographie
    0.63
    сылкі
    0.63
    Activations Density 0.409%

    No Known Activations