INDEX

Explanations

the word "vice"

oai_token-act-pair · gemini-2.0-flash

vice

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

-1.15

 Theſe

-1.02

Efq

-0.98

-0.95

 itſelf

-0.94

sizeCache

-0.94

 AssemblyTitle

-0.94

IRUS

-0.91

 purpoſe

-0.91

 Anſ

-0.91

POSITIVE LOGITS

the

0.81

and

0.80

0.74

his

0.65

 some

0.63

0.62

the

0.60

0.59

any

0.56

0.55

Activations Density 0.564%

the word "vice"

vice

No Comments

No Known Activations