© 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. 8749
    Prev
    Next
    INDEX
    Explanations

    code snippets, including definitions, assignments, and calculations

    oai_token-act-pair · gemini-2.0-flash

    real estate

    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
     [(
    -1.28
    [(
    -1.25
     ((
    -1.20
    ((
    -1.19
    )=(
    -1.16
    =(
    -1.11
    :(
    -1.09
    /(
    -1.09
    \{(
    -1.08
    }=(
    -1.07
    POSITIVE LOGITS
     housing
    2.05
    Housing
    1.96
     Housing
    1.95
     HOUSING
    1.80
    housing
    1.76
     residential
    1.66
     Residential
    1.58
    Residential
    1.52
    residential
    1.48
     apartment
    1.33
    Activations Density 3.504%

    No Known Activations