INDEX

Explanations

the word "peace"

oai_token-act-pair · gemini-2.0-flash

the concept of peace

np_token-act-pair-logits · gpt-4o-mini

peace

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ViewImports

-0.65

енча

-0.56

">//

-0.55

Autoritní

-0.53

 useState

-0.53

 ſtate

-0.52

NOPQRST

-0.52

 صوتيه

-0.51

nodoc

-0.49

paramref

-0.48

POSITIVE LOGITS

fully

0.63

 tartalomajánló

0.62

ful

0.62

full

0.60

FULLY

0.60

 незавершена

0.59

 fully

0.54

FUL

0.54

letus

0.54

SequentialGroup

0.53

Activations Density 0.533%

the word "peace"

the concept of peace

peace

No Comments

No Known Activations