© 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. 15026
    Prev
    Next
    INDEX
    Explanations

    somewhat random English language words or parts of words

    oai_token-act-pair · gemini-2.0-flash

    say "N" words

    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
     MessageBoxIcon
    -0.72
     n
    -0.64
    nt
    -0.64
    nd
    -0.61
     nd
    -0.58
    RegressionTest
    -0.57
    le
    -0.57
    ne
    -0.54
     nt
    -0.52
    ny
    -0.50
    POSITIVE LOGITS
    N
    0.81
    NIF
    0.66
    NQ
    0.61
    NID
    0.60
    NEGATIVE
    0.58
    NIN
    0.56
    RenderAtEndOf
    0.56
     Reverso
    0.56
     <<<<<<<<<<<<<<
    0.55
    стюм
    0.55
    Activations Density 2.269%

    No Known Activations