INDEX

Explanations

java code

oai_token-act-pair · gemini-2.0-flash

Code logs

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 greateſt

-0.66

 myſelf

-0.66

 pleaſure

-0.64

 Shakspeare

-0.63

 neceff

-0.63

lgari

-0.63

 purpoſe

-0.61

 Monfieur

-0.60

 whoſe

-0.60

AndEndTag

-0.60

POSITIVE LOGITS

0.56

gy

0.50

 saisir

0.49

—

0.49

0.48

der

0.47

，「

0.47

 ()=>{

0.47

CHANT

0.45

BuildContext

0.44

Activations Density 7.847%

java code

Code logs

No Comments

No Known Activations