© 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. 14835
    Prev
    Next
    INDEX
    Explanations

    astrological or personality trait terms

    oai_token-act-pair · gemini-2.0-flash

    religion/astrology/cycles

    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
     surla
    -0.57
    }")
    -0.56
     }}">
    -0.55
    apollo
    -0.51
    हार
    -0.51
    脚注の使い方
    -0.51
    蚪
    -0.50
    IVEREF
    -0.49
    __':
    -0.48
    ')}}">
    -0.48
    POSITIVE LOGITS
     Dign
    0.56
     transfusion
    0.55
     tubercle
    0.54
     officinalis
    0.53
     Maximus
    0.52
     therapy
    0.51
    حياتها
    0.49
     smtplib
    0.48
    thenia
    0.48
    OwnProperty
    0.48
    Activations Density 13.276%

    No Known Activations