INDEX

Explanations

words or short phrases expressing a softening of position or a reduction/removal of something.

oai_token-act-pair · gemini-2.0-flash

gene silencing and quietness

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

rouvez

-0.53

 seno

-0.49

ω

-0.49

ArgumentParser

-0.48

 Felicia

-0.47

 menyes

-0.47

endswith

-0.47

搬

-0.47

 rodi

-0.47

ady

-0.46

POSITIVE LOGITS

 silence

0.93

silence

0.81

 silent

0.80

Silence

0.77

silent

0.76

Silen

0.75

 Silence

0.75

SourceChecksum

0.74

 propOrder

0.74

silen

0.73

Activations Density 0.891%

words or short phrases expressing a softening of position or a reduction/removal of something.

gene silencing and quietness

No Known Activations