© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12391
    Prev
    Next
    INDEX
    Explanations

    an IPv6 address containing colons

    oai_token-act-pair · gemini-2.0-flash

    self-referential terms and identifiers

    np_token-act-pair-logits · gpt-4o-mini

    code and identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     d
    -0.47
     e
    -0.47
     da
    -0.45
    __(/*!
    -0.44
     f
    -0.43
     labios
    -0.42
     m
    -0.41
     r
    -0.40
     je
    -0.40
     con
    -0.39
    POSITIVE LOGITS
     itſelf
    1.16
     myſelf
    1.14
    #+#
    1.13
     CWE
    1.08
     Efq
    1.04
    ſelf
    1.00
    ſelves
    1.00
     ſeveral
    0.98
    UnknownFields
    0.94
    ^(@)
    0.93
    Activations Density 0.723%

    No Known Activations