INDEX

Explanations

web addresses and URLs.

oai_token-act-pair · gemini-2.0-flash

.co

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

 Varela

-0.54

ISTO

-0.51

 elongated

-0.51

 thawing

-0.47

 fevere

-0.47

 Delano

-0.47

Devo

-0.47

 fables

-0.47

 prosthesis

-0.47

]--;

-0.47

POSITIVE LOGITS

 disambiguazione

0.69

gj

0.57

Източници

0.56

évaluateur

0.56

 CreateTagHelper

0.54

extAlignment

0.52

 preuves

0.51

 venons

0.51

 santiago

0.50

Personendaten

0.50

Activations Density 12.483%

web addresses and URLs.

.co

No Comments

No Known Activations