© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13542
    Prev
    Next
    INDEX
    Explanations

    the letter "f" followed by a single character and code

    oai_token-act-pair · gemini-2.0-flash

    f

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     f
    -2.16
    <bos>
    -1.41
     F
    -0.96
     b
    -0.71
     t
    -0.68
     ф
    -0.63
     fo
    -0.62
    ｆ
    -0.62
     j
    -0.62
    ’
    -0.62
    POSITIVE LOGITS
     houſe
    0.93
     stiefel
    0.88
     myſelf
    0.86
     pleaſure
    0.84
     ―――――
    0.84
    wiſe
    0.84
     Houſe
    0.81
     cauſe
    0.80
     Majefty
    0.79
     auffi
    0.79
    Activations Density 2.134%

    No Known Activations