INDEX

Explanations

speech and salutations.

oai_token-act-pair · gemini-2.0-flash

Dialogue

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

 self

-0.48

MTI

-0.46

vikle

-0.45

sk

-0.44

-0.43

 cellspacing

-0.43

щите

-0.42

 esca

-0.41

strongly

-0.41

POSITIVE LOGITS

GOTREF

0.92

OGND

0.90

 itſelf

0.88

 themſelves

0.85

 himſelf

0.81

 Theſe

0.78

 leſs

0.75

 ſtand

0.73

fromnode

0.72

 myſelf

0.72

Activations Density 0.793%

speech and salutations.

Dialogue

No Comments

No Known Activations