© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4033
    Prev
    Next
    INDEX
    Explanations

    the pronoun "you" and question words

    oai_token-act-pair · gemini-2.0-flash

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    íncia
    -0.68
     tillegg
    -0.64
    ignty
    -0.63
    tráfico
    -0.63
    žová
    -0.62
    gående
    -0.60
    зулта
    -0.60
    :✨
    -0.59
    zeß
    -0.59
    ingway
    -0.59
    POSITIVE LOGITS
    r
    0.68
    Geplaatst
    0.53
     a
    0.51
    g
    0.51
    j
    0.51
     محفوظة
    0.50
    v
    0.50
    OGND
    0.50
    JoinColumn
    0.50
    tir
    0.49
    Activations Density 13.687%

    No Known Activations