© 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. 7710
    Prev
    Next
    INDEX
    Explanations

    phrases indicating categories of people, especially age ranges.

    oai_token-act-pair · gemini-2.0-flash

    words related to creative writing

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

    age and youth

    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
     young
    -1.74
    young
    -1.52
    Young
    -1.34
     YOUNG
    -1.31
     younger
    -1.28
     jonge
    -1.24
     giovane
    -1.24
     Young
    -1.20
     jeune
    -1.19
    YOUNG
    -1.19
    POSITIVE LOGITS
    PointerException
    0.55
    esti
    0.45
    writers
    0.44
     writers
    0.43
    Writers
    0.42
    ünstler
    0.41
    ata
    0.40
     hóspedes
    0.40
    tie
    0.39
    сен
    0.39
    Activations Density 1.067%

    No Known Activations