© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4020
    Prev
    Next
    INDEX
    Explanations

    code snippets including variable declarations and potentially JSON parsing

    oai_token-act-pair · gemini-2.0-flash

    code syntax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ’
    -0.69
    '
    -0.45
     Minimize
    -0.43
    –
    -0.43
    9
    -0.42
    ‘
    -0.42
     diversi
    -0.41
    1
    -0.41
    0
    -0.41
     ’
    -0.40
    POSITIVE LOGITS
    findpost
    0.85
     AssemblyCompany
    0.77
     }}"></
    0.72
    ########.
    0.69
    DebuggerStep
    0.65
    ConstraintMaker
    0.65
     propOrder
    0.65
    IVEREF
    0.65
    脚注の使い方
    0.65
     }=\
    0.65
    Activations Density 5.872%

    No Known Activations