© 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. 6126
    Prev
    Next
    INDEX
    Explanations

    contractions with "not" and adjectives describing when something happened

    oai_token-act-pair · gemini-2.0-flash

    words starting with 't'

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

    Negative past experiences

    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
     незавершена
    -0.81
    AnimationsModule
    -0.72
    XmlAccessorType
    -0.71
     متعلقه
    -0.69
     विश्वसनीयता
    -0.66
     صوتيه
    -0.66
    IsMutable
    -0.64
    Atsauces
    -0.63
     CommonModule
    -0.62
    ValueStyle
    -0.60
    POSITIVE LOGITS
     cared
    0.55
    <bos>
    0.52
    für
    0.45
    endcsname
    0.45
     exact
    0.41
     lived
    0.41
     viewed
    0.41
     deleteById
    0.41
    udnio
    0.41
     liked
    0.41
    Activations Density 1.136%

    No Known Activations