© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6330
    Prev
    Next
    INDEX
    Explanations

    words describing artistic or technical skills

    oai_token-act-pair · gemini-2.0-flash

    words related to photography and visual media

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

    photography

    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
     ریزی
    -0.46
    をチェック
    -0.42
    katapos
    -0.41
     Пусть
    -0.40
     gio
    -0.40
     Stays
    -0.40
     otomatig
    -0.40
     bords
    -0.40
    istema
    -0.40
     compagn
    -0.39
    POSITIVE LOGITS
     photography
    0.92
     photographers
    0.82
     photographic
    0.81
     fotográfico
    0.80
     Photographic
    0.77
     cinematography
    0.76
     photographing
    0.75
     CreateTagHelper
    0.75
     graphic
    0.74
     VFX
    0.74
    Activations Density 5.543%

    No Known Activations