INDEX

Explanations

phrases denoting long time spans

oai_token-act-pair · gemini-2.0-flash

say "term"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

basicConfig

-0.69

AndroidJUnit

-0.65

 long

-0.60

 paramInt

-0.60

Hochspringen

-0.58

ècie

-0.57

RegistryLite

-0.56

Дереккөздер

-0.56

VideoCapture

-0.55

dellín

-0.54

POSITIVE LOGITS

 term

0.69

term

0.65

 TERM

0.57

RANGE

0.56

 onAnimation

0.56

Term

0.54

range

0.54

 terms

0.49

WebControls

0.48

 Term

0.48

Activations Density 0.349%

phrases denoting long time spans

say "term"

No Comments

No Known Activations