© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5432
    Prev
    Next
    INDEX
    Explanations

    the word "in" and nearby short words like "for", "at", and "of"

    oai_token-act-pair · gemini-2.0-flash

    Complex sentences

    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
    -}
    -0.60
    bigsqcup
    -0.59
    Tikang
    -0.54
    ")(
    -0.54
    -)
    -0.53
     SwitchCompat
    -0.53
    )^{-
    -0.52
    -</
    -0.52
    :+:
    -0.51
    #+#
    -0.51
    POSITIVE LOGITS
     himſelf
    0.77
     themſelves
    0.67
     nhau
    0.66
     myſelf
    0.61
    ſelf
    0.61
     ſhe
    0.60
     ſhall
    0.60
     becauſe
    0.59
     itſelf
    0.59
     Jefus
    0.58
    Activations Density 7.100%

    No Known Activations