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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11421
    Prev
    Next
    INDEX
    Explanations

    the name "Frank"

    oai_token-act-pair · gemini-2.0-flash

    Frank

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    assertThat
    -0.42
     vz
    -0.41
     odw
    -0.41
    ollectionView
    -0.39
    Works
    -0.39
    ient
    -0.39
     gron
    -0.38
    во
    -0.37
    str
    -0.37
    Whoosh
    -0.37
    POSITIVE LOGITS
    AndEndTag
    0.97
     utafitiHapana
    0.89
    AnchorStyles
    0.88
    InitVars
    0.84
    ----</
    0.77
    LookAnd
    0.77
    #+#
    0.76
    HasAnnotation
    0.74
    setVerticalGroup
    0.73
     AssemblyProduct
    0.70
    Activations Density 0.328%

    No Known Activations