© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2516
    Prev
    Next
    INDEX
    Explanations

    question and answer pairs

    oai_token-act-pair · gemini-2.0-flash

    tokens representing various types of queries or prompts

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

    Questions and/or the name "Ann"

    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
    tvguidetime
    -0.84
    RTCF
    -0.61
    kuuta
    -0.60
     intptr
    -0.60
     estekak
    -0.60
    Gön
    -0.59
     snippetHide
    -0.59
     Edge
    -0.56
    RUnlock
    -0.55
     noqa
    -0.54
    POSITIVE LOGITS
    المناصب
    0.51
    iotensin
    0.47
    iastes
    0.46
    cimento
    0.46
    expandindo
    0.45
    Népesség
    0.45
     OFDb
    0.45
    ancers
    0.44
    KindOfClass
    0.44
    igshid
    0.44
    Activations Density 0.010%

    No Known Activations