© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4253
    Prev
    Next
    INDEX
    Explanations

    mentions of the number of characters in a string or array

    oai_token-act-pair · gemini-2.0-flash

    length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     length
    -2.64
    length
    -2.45
     Length
    -2.33
    Length
    -2.28
     lengths
    -2.14
     LENGTH
    -2.08
     lenght
    -2.05
    LENGTH
    -1.88
     Länge
    -1.71
    lengths
    -1.68
    POSITIVE LOGITS
     consistent
    0.42
    hintText
    0.41
    паси
    0.41
     Consistent
    0.40
    FromArgb
    0.38
    tel
    0.36
    <eos>
    0.35
    вались
    0.35
    tabular
    0.35
    кор
    0.35
    Activations Density 3.940%

    No Known Activations