INDEX

Explanations

year ranges, along with some terms related to education, awards and organizations/cities

oai_token-act-pair · gemini-2.0-flash

Months

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

awtextra

-1.08

قایناق‌لار

-0.99

 nakalista

-0.99

 ujednoznacz

-0.87

 مشين

-0.85

tvguidetime

-0.82

MessageOf

-0.79

saraba

-0.79

stdc

-0.79

ьаж

-0.79

POSITIVE LOGITS

0.91

 December

0.90

 January

0.89

 November

0.88

 February

0.87

 April

0.86

 September

0.85

 October

0.85

 July

0.79

 March

0.79

Activations Density 1.944%

year ranges, along with some terms related to education, awards and organizations/cities

Months

No Comments

No Known Activations