INDEX

Explanations

tokens related to money and/or financial situations

oai_token-act-pair · gemini-2.0-flash

foreign languages

np_token-act-pair-logits · gemini-2.0-flash

non-English text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 funding

-0.72

 cost

-0.71

 funds

-0.68

 Cost

-0.66

 money

-0.65

 financi

-0.64

 costs

-0.63

 expensive

-0.63

cost

-0.60

 cash

-0.59

POSITIVE LOGITS

 Мексичка

0.71

তথ্যসূত্র

0.69

 &___

0.68

<()>

0.66

脚注の使い方

0.65

клопе

0.63

 ProtoMessage

0.60

 العنوان

0.60

 potency

0.60

itinéraire

0.59

Activations Density 3.085%

tokens related to money and/or financial situations

foreign languages

non-English text

No Comments

No Known Activations