INDEX

Explanations

mentions of the existence of something at a location

oai_token-act-pair · gemini-2.0-flash

there

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 TextInputType

-0.66

 purpoſe

-0.60

batore

-0.60

 caufe

-0.59

();)

-0.56

 beſt

-0.54

 كومونز

-0.52

 doubtnut

-0.51

ADELPHIA

-0.50

 deſt

-0.50

POSITIVE LOGITS

лтемелер

0.61

 Roskov

0.51

Rujuakan

0.50

 kasarigan

0.50

0.48

'@/

0.47

 Bertram

0.46

is

0.46

Зноскі

0.45

櫥

0.44

Activations Density 0.256%

mentions of the existence of something at a location

there

No Comments

No Known Activations