INDEX

Explanations

verbs that indicate an action or state of being

oai_token-act-pair · gemini-2.0-flash

noises

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

orté

-0.64

 vastaan

-0.59

 faixa

-0.56

ReusableCell

-0.56

 partagé

-0.54

encodeWith

-0.54

 graça

-0.53

 calore

-0.53

ároz

-0.52

 kanssa

-0.52

POSITIVE LOGITS

 незавершена

0.83

DidLoad

0.64

 pinulongan

0.59

 Audiodateien

0.57

BeginInit

0.55

 disambiguazione

0.54

 OFDb

0.52

principalTable

0.51



0.50

Jeografia

0.47

Activations Density 10.429%

verbs that indicate an action or state of being

noises

No Comments

No Known Activations