© 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. 6267
    Prev
    Next
    INDEX
    Explanations

    the word "True" and maybe related concepts like truth or certainty

    oai_token-act-pair · gemini-2.0-flash

    affirmative statements

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

    True

    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
     marquées
    -0.64
     dévelo
    -0.62
     fournis
    -0.58
     suivants
    -0.55
     posibles
    -0.55
    日閲覧
    -0.54
     chimiques
    -0.54
     scolaires
    -0.54
     démocr
    -0.53
     fournies
    -0.51
    POSITIVE LOGITS
    uxxxx
    0.71
    ValueStyle
    0.69
    piram
    0.69
    MigrationBuilder
    0.68
    StoryboardSegue
    0.64
     ویکی‌پدی
    0.64
    agisse
    0.64
    UnsafeEnabled
    0.63
    XMLSchema
    0.63
    GOTREF
    0.61
    Activations Density 4.032%

    No Known Activations