INDEX

Explanations

the word "wear," sometimes in the context of alcohol

oai_token-act-pair · gemini-2.0-flash

wear

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTSDATUM

-0.76

IntoConstraints

-0.72

CloseOperation

-0.71

transQ

-0.67

Portale

-0.66

Rüyada

-0.66

 createSprite

-0.65

amssymb

-0.65

MemoryWarning

-0.63

Abit

-0.59

POSITIVE LOGITS

 Theſe

0.97

 itſelf

0.95

 myſelf

0.87

 Shakspeare

0.84

 againſt

0.80

 faſt

0.79

 uſed

0.79

ſelf

0.79

 himſelf

0.77

"\<

0.75

Activations Density 2.661%

the word "wear," sometimes in the context of alcohol

wear

No Comments

No Known Activations