© 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. 8130
    Prev
    Next
    INDEX
    Explanations

    a variety of uncommon word prefixes like "dom-", "rom-", and "som-".

    oai_token-act-pair · gemini-2.0-flash

    romantic themes or tropes

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

    rom

    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
    dorff
    -0.54
    guenos
    -0.47
    mayr
    -0.46
     thiệu
    -0.46
     ویکی‌پدی
    -0.45
     '}
    -0.44
    ]--;
    -0.43
    mehr
    -0.42
     Martin
    -0.42
    mbitos
    -0.42
    POSITIVE LOGITS
    #+#
    0.71
    Espèce
    0.70
     AttributeSet
    0.66
    phosa
    0.63
    InputBorder
    0.61
    BlockPos
    0.60
    InjectMocks
    0.59
    ArgsConstructor
    0.59
    pédie
    0.58
    WithMany
    0.58
    Activations Density 0.428%

    No Known Activations