© 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. 14507
    Prev
    Next
    INDEX
    Explanations

    javascript code syntax

    oai_token-act-pair · gemini-2.0-flash

    identity

    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
     Container
    -1.84
     container
    -1.80
    container
    -1.73
     Containers
    -1.71
     containers
    -1.68
    Container
    -1.65
    Containers
    -1.59
     vessels
    -1.50
    containers
    -1.49
    CONTAINER
    -1.48
    POSITIVE LOGITS
     identity
    1.85
     Identity
    1.80
     identification
    1.80
     Identification
    1.75
     identities
    1.74
     Identi
    1.73
    Identi
    1.73
     identi
    1.70
    identity
    1.70
    Identification
    1.69
    Activations Density 1.691%

    No Known Activations