INDEX

Explanations

sentences making a comparison (often with "more", "than").

oai_token-act-pair · gemini-2.0-flash

further

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

bootstrapcdn

-0.68

 незавершена

-0.65

 nakalista

-0.65

verifyException

-0.57

 estekak

-0.52

 оригіналу

-0.51

NameInMap

-0.50

 henvisninger

-0.50

 CYTHON

-0.50

 nahilalakip

-0.48

POSITIVE LOGITS

 further

3.81

further

3.55

Further

3.30

 Further

3.27

 FURTHER

3.13

FURTHER

2.59

进一步

1.98

 farther

1.92

urther

1.78

 verder

1.75

Activations Density 6.759%

sentences making a comparison (often with "more", "than").

further

No Comments

No Known Activations