© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8970
    Prev
    Next
    INDEX
    Explanations

    the mathematical notation "**", likely signifying exponentiation

    oai_token-act-pair · gemini-2.0-flash

    **

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    "
    -1.19
    **
    -1.12
    “
    -1.09
    ”
    -1.06
    ''
    -0.99
     "
    -0.94
     “
    -0.88
     ”
    -0.85
     **
    -0.84
    ("
    -0.81
    POSITIVE LOGITS
     صوتيه
    1.05
     myſelf
    1.03
    findpost
    1.01
     للاسماء
    0.98
    IntoConstraints
    0.94
     ویکی‌پدیا
    0.90
     يتيمه
    0.90
     purpoſe
    0.90
     houſe
    0.86
    providedIn
    0.85
    Activations Density 1.195%

    No Known Activations