© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 15961
    Prev
    Next
    INDEX
    Explanations

    questions with an answer attached in a dialog format

    oai_token-act-pair · gemini-2.0-flash

    question and answer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     а
    -0.92
    a
    -0.90
     B
    -0.88
    а
    -0.81
    B
    -0.77
     a
    -0.73
     C
    -0.71
     D
    -0.68
     O
    -0.66
    C
    -0.66
    POSITIVE LOGITS
     يتيمه
    0.88
    TypedDataSet
    0.82
    WithIOException
    0.80
    }],
    
    0.76
    دانشنامهٔ
    0.76
     autorytatywna
    0.72
    TagHelper
    0.71
    ⓧ
    0.71
    ,:);
    0.71
    PerformLayout
    0.70
    Activations Density 1.294%

    No Known Activations