INDEX

Explanations

the word "full"

oai_token-act-pair · gemini-2.0-flash

full

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

VersionUID

-0.68

 coû

-0.60

 ""],

-0.55

 feroit

-0.53

 verdadeiro

-0.52

 Protección

-0.50

 незавершена

-0.50

 universale

-0.50

 perciò

-0.49

maked

-0.49

POSITIVE LOGITS

ỡng

0.56

 CreateTagHelper

0.54

IsContent

0.54

Décès

0.51

帖最后由

0.50

ClientSize

0.50

سطس

0.48

DoubleQuotes

0.46

범

0.45

GraphicsUnit

0.45

Activations Density 0.456%

the word "full"

full

No Comments

No Known Activations