© 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. 6340
    Prev
    Next
    INDEX
    Explanations

    the word "too"

    oai_token-act-pair · gemini-2.0-flash

    the word "too"

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

    too

    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
    IsMutable
    -1.03
    UrlResolution
    -0.98
     Normdatei
    -0.94
    AsUp
    -0.93
    enterOuterAlt
    -0.91
     وتسجيلات
    -0.91
     '\\;'
    -0.85
    complexContent
    -0.85
     unknownFields
    -0.84
    LookAnd
    -0.84
    POSITIVE LOGITS
     large
    0.42
     wide
    0.38
    IPS
    0.36
     also
    0.35
     huge
    0.35
     تعدى
    0.32
     MongoClient
    0.32
    .
    0.31
     old
    0.31
    amp
    0.31
    Activations Density 1.870%

    No Known Activations