INDEX

Explanations

code-related text containing string concatenations and database queries

oai_token-act-pair · gemini-2.0-flash

Quotation marks

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 disambiguazione

-0.87

 ploughing

-0.64

 plowing

-0.63

 termica

-0.59

Zeneca

-0.59

Enders

-0.59

 Réponses

-0.56

 alimentare

-0.54

جوايز

-0.54

 scolaires

-0.54

POSITIVE LOGITS

(/\

0.52

,"%

0.50

'{@

0.48

tagHelper

0.47

([]

0.47

(),"

0.47

("$.

0.47

'%

0.47

len

0.47

val

0.46

Activations Density 7.433%

code-related text containing string concatenations and database queries

Quotation marks

No Comments

No Known Activations