INDEX

Explanations

words related to rivers, water, banks, and measuring land

oai_token-act-pair · gemini-2.0-flash

river

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

ValueStyle

-0.56

 CURIAM

-0.56

moz

-0.54

kkelen

-0.53

xampp

-0.49

 hende

-0.46

adrez

-0.46

 materna

-0.46

XmlRootElement

-0.45

-------------</

-0.45

POSITIVE LOGITS

 bank

1.40

 banks

1.39

bank

1.30

banks

1.21

BANK

1.09

 BANKS

1.07

Bank

1.07

 BANK

1.05

Banks

1.05

 Banks

1.05

Activations Density 0.815%

words related to rivers, water, banks, and measuring land

river

No Comments

No Known Activations