© 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. 6188
    Prev
    Next
    INDEX
    Explanations

    fairly common and generic words like 'out', 'is', 'in', 'to', 'be', and 'on'

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    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
    Here
    -0.70
     Here
    -0.69
    Those
    -0.68
    Different
    -0.66
    Through
    -0.66
     Those
    -0.66
    That
    -0.66
    Then
    -0.65
    Various
    -0.65
    Also
    -0.64
    POSITIVE LOGITS
     their
    1.54
     themselves
    1.07
    their
    1.04
     ihre
    1.02
     ihrer
    0.95
     ihrem
    0.91
     ihren
    0.90
     ihr
    0.83
     theirs
    0.80
     propOrder
    0.79
    Activations Density 21.753%

    No Known Activations