INDEX

Explanations

phrases using "down" or "put."

oai_token-act-pair · gemini-2.0-flash

non-English language

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 down

-2.77

down

-2.27

Down

-2.22

 Down

-2.13

 DOWN

-2.09

DOWN

-1.82

downs

-1.55

 downs

-1.39

ダウン

-1.34

Downs

-1.24

POSITIVE LOGITS

Hochspringen

0.55

iettes

0.50

izmu

0.50

 المعيارى

0.49

usermodel

0.49

uestions

0.49

 Freestyle

0.48

Hauptartikel

0.48

같이

0.48

 Signalez

0.47

Activations Density 3.395%

phrases using "down" or "put."

non-English language

No Comments

No Known Activations